Preperation for merging multiple conllus, also added ATE files

ATEapi/.dockerignore

@@ -0,0 +1,26 @@
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/bin
+**/charts
+**/docker-compose*
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+README.md

ATEapi/.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+.DS_Store
+.vscode/
+model/term_extractor/pytorch_model.bin

ATEapi/Dockerfile

@@ -0,0 +1,28 @@
+# For more information, please refer to https://aka.ms/vscode-docker-python
+FROM python:3.8
+
+EXPOSE 5000
+
+# Keeps Python from generating .pyc files in the container
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Turns off buffering for easier container logging
+ENV PYTHONUNBUFFERED=1
+
+# RUN apk add --no-cache gcc musl-dev
+RUN pip install gunicorn
+
+# Install pip requirements
+COPY requirements.txt .
+RUN python -m pip install -r requirements.txt
+
+WORKDIR /app
+COPY . /app
+
+# Creates a non-root user with an explicit UID and adds permission to access the /app folder
+# For more info, please refer to https://aka.ms/vscode-docker-python-configure-containers
+RUN adduser -u 5678 --disabled-password --gecos "" appuser && chown -R appuser /app
+USER appuser
+
+# During debugging, this entry point will be overridden. For more information, please refer to https://aka.ms/vscode-docker-python-debug
+CMD ["gunicorn", "--bind", "0.0.0.0:5000", "main:app"]

ATEapi/README.md

@@ -0,0 +1,57 @@
+# Automatic Term Extraction API
+
+## 1. Description
+In this repo, we wrote an API to inference SloBERTa term extractor, whose model has been trained with [RSDO5 corpus](https://www.clarin.si/repository/xmlui/handle/11356/1400). Feel free to check out this [repo](https://github.com/honghanhh/ate-2022) for better understanding about the methodology.
+
+---
+
+## 2. Requirements
+
+Please install all the necessary libraries noted in [requirements.txt](./requirements.txt) using this command:
+
+```
+pip install -r requirements.txt
+```
+
+## 3. Implementation
+
+Download the model from [pytorch_model.bin](https://kt-cloud.ijs.si/index.php/s/T4qtSKxbxgqr6c5) and save it into `./model/term_extractor/`.
+
+Run the following command on the terminal:
+
+```python
+main.py
+```
+
+A link will be show on the terminal so that you can access to the API and test requests.
+```python
+ * Serving Flask app 'main'
+ * Debug mode: on
+WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
+ * Running on http://127.0.0.1:5000
+Press CTRL+C to quit
+ * Restarting with stat
+ * Debugger is active!
+ * Debugger PIN: 185-520-689
+```
+
+We suggest you use POSTMAN or Hoppscotch to test the API with an uploaded file as the output whose format is CONLL-like (plese check out [temp_1.conllu](temp_1.conllu)). See the demonstration as the image below.
+
+![demo](./imgs/demo.png)
+
+## 4. Docker version
+Run the following command:
+```python
+docker build -t ate .  
+docker run -d -p 5000:5000 ate
+```
+
+## 5. References
+The term extraction tool is an updated version of Tran et al. (2022), using the SloBERTa model.
+
+Hanh Thi Hong Tran, Matej Martinc, Andraz Repar, Antoine Doucet and Senja Pollak: A Transformer-based Sequence-labeling Approach to the Slovenian Cross-domain Automatic Term Extraction. Proc. of Jezikovne tehnologije in digitalna humanistika, 2022.
+
+## 6. Contributors:
+- 🐮 [TRAN Thi Hong Hanh](https://github.com/honghanhh) 🐮
+- Matej Martinc
+- Senja Pollak

ATEapi/canonical_utils.py

@@ -0,0 +1,108 @@
+import os
+import classla
+# classla.download('sl', logging_level='WARNING')
+
+from lemmagen3 import Lemmatizer
+
+def lem_adj(gender, wrd):
+    lem = Lemmatizer()
+    if gender == 'm':
+        lem.load_model(os.path.join('./model/lemmagen_models/kanon-adj-male.bin'))
+    elif gender == 'f':
+        lem.load_model(os.path.join('./model/lemmagen_models/kanon-adj-female.bin'))
+    elif gender == 'n':
+        lem.load_model(os.path.join('./model/lemmagen_models/kanon-adj-neutral.bin'))
+
+    form = lem.lemmatize(wrd)
+    return form
+
+
+def process_nlp_pipeline(lang, text):
+    nlp = classla.Pipeline(lang=lang, processors='tokenize,pos,lemma', tokenize_pretokenized=True, logging_level='WARNING')
+    doc = nlp(text)
+    return doc
+
+
+def get_adj_msd(head, word):
+    feats = head.feats
+    feats_dict = {}
+    feats = feats.strip().split('|')
+    for f in feats:
+        f = f.strip().split('=')
+        feats_dict[f[0]] = f[1]
+    gender = feats_dict['Gender']
+    #print(gender)
+    #gender = gender.strip().split('=')[1]
+    if gender == 'Masc' and len(word.xpos) == 6:
+        msd = word.xpos[:-1]+'ny'
+    elif gender == 'Masc' and len(word.xpos) == 7:
+        msd = word.xpos[:-1]+'y'
+    elif gender == 'Fem':
+        msd = word.xpos[:-1]+'n'
+    elif gender == 'Neut':
+        msd = word.xpos[:-1]+'n'
+    else:
+        msd = None
+    return msd
+
+
+def subfinder(mylist, pattern):
+    matches = []
+    for i in range(len(mylist)):
+        if mylist[i].text.lower() == pattern[0] and [t.text.lower() for t in mylist[i:i+len(pattern)]] == pattern:
+            matches.append(mylist[i:i+len(pattern)])
+    return matches
+
+
+def find_canon(term):
+    head = None
+    pre = []
+    post = []
+    for word in term.words:
+        if word.upos == 'NOUN' or word.upos == 'PROPN':
+            head = word
+            break
+    if head is None:
+        if len(term.words) == 1:
+            head2 = term.words[0]
+            lem = Lemmatizer()
+            lem.load_model(os.path.join('./model/lemmagen_models/kanon.bin'))
+            head_form = lem.lemmatize(head2.text.lower())
+            return head_form
+        else:
+            return ' '.join([w.text for w in term.words])  # just return the input because we do not cover such case
+    else:
+        for word in term.words:
+            if word.id < head.id:
+                pre.append(word)
+            elif word.id > head.id:
+                post.append(word)
+
+    canon = []
+    for el in pre:
+        msd = get_adj_msd(head, el)
+        if msd is None:
+            canon.append(el.lemma.lower())
+        else:
+            if msd[0] == 'A' and msd[3] == 'm':
+                form = lem_adj('m', el.text.lower())
+                canon.append(form)
+            elif msd[0] == 'A' and msd[3] == 'f':
+                form = lem_adj('f', el.text.lower())
+                canon.append(form)
+            elif msd[0] == 'A' and msd[3] == 'n':
+                form = lem_adj('n', el.text.lower())
+                canon.append(form)
+
+    lem = Lemmatizer()
+    lem.load_model(os.path.join('./model/lemmagen_models/kanon.bin'))
+    head_form = lem.lemmatize(head.text.lower())
+    canon.append(head_form)
+    for el in post:
+        canon.append(el.text)
+    return ' '.join(canon)
+
+def process(forms):
+    text = '\n'.join(forms)
+    doc = process_nlp_pipeline('sl', text)
+    return [find_canon(sent) for sent in doc.sentences]

ATEapi/docker-compose.debug.yml

@@ -0,0 +1,14 @@
+version: '3.4'
+
+services:
+  atedocker:
+    image: atedocker
+    build:
+      context: .
+      dockerfile: ./Dockerfile
+    command: ["sh", "-c", "pip install debugpy -t /tmp && python /tmp/debugpy --wait-for-client --listen 0.0.0.0:5678 -m flask run --no-debugger --no-reload --host 0.0.0.0 --port 5000"]
+    ports:
+      - 5000:5000
+      - 5678:5678
+    environment:
+      - FLASK_APP=main.py

ATEapi/docker-compose.yml

@@ -0,0 +1,10 @@
+version: '3.4'
+
+services:
+  atedocker:
+    image: atedocker
+    build:
+      context: .
+      dockerfile: ./Dockerfile
+    ports:
+      - 5001:5000

ATEapi/main.py

@@ -0,0 +1,67 @@
+# Dependencies
+import torch
+import torch.nn.functional as F
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+from utils import *
+from canonical_utils import *
+from flask import Flask, request, jsonify
+from transformers import AutoTokenizer, AutoModelForTokenClassification 
+
+# Your API definition
+app = Flask(__name__)
+
+label_list=["n", "B-T", "T"]
+tokenizer = AutoTokenizer.from_pretrained('./model/term_extractor/')
+model = AutoModelForTokenClassification.from_pretrained('./model/term_extractor/', num_labels=len(label_list)).to(device)
+
+@app.route('/predict',methods=['POST'])
+def predict():
+    frame = read_conll(request.files['file'])
+    sequences = [' '.join(x) for x in frame.word]
+    lemma, pos, msd = frame.lemma, frame.pos, frame.msd
+    preds = []
+    probs = []
+    for seq in sequences:
+        tokens = tokenizer(seq, padding=True, truncation=True, return_tensors="pt").to(device)
+        output = model(**tokens).logits.argmax(-1)
+        prob = F.softmax(model(**tokens).logits, dim=2)
+        probs.append(prob[0].tolist())
+        preds.append([label_list[key] for key in output[0].tolist()])
+
+    texts, final_preds, final_probs = [], [], []
+    for seq, pred, prob in list(zip(sequences, preds, probs)):
+        t, p, p1 = remap(tokenizer, seq, pred, prob)
+        texts.append(t)
+        final_preds.append(p)
+        final_probs.append(p1)
+    predicted_terms, prob_terms, lemma_terms, pos_terms, msd_terms = extract_terms_full(final_preds, final_probs, texts, lemma, pos, msd)
+    df = pd.DataFrame({'terms':predicted_terms,
+                    'raw_prob':prob_terms,
+                    'lemma':lemma_terms,
+                    'pos':pos_terms,
+                    'msd':msd_terms})
+    df = df.drop_duplicates(subset=['lemma','pos'], keep='first')
+    # print(df.head(5))
+    df['prob'] = pd.Series(dtype='float')
+    for i in range(len(df)):
+        temp = [float(x) for x in df['raw_prob'].iloc[i].split(' ')]
+        df['prob'].iloc[i] = round(sum(temp)/len(temp),4)
+
+    df = df.sort_values(by=['lemma','prob'], ascending=True)
+    df = df.drop_duplicates(subset=['lemma'], keep='last')
+    df['canonical'] = process(df['terms'])
+    df = df[['terms', 'canonical', 'lemma','pos','msd','prob']].rename(columns={'prob':'ranking'})
+    # sort by ranking 
+    # print(df.head(5))
+    df = df[df['pos'] != 'PUNCT']
+    df = df.query("terms.str.len() > 2")
+    df = df.sort_values('ranking', ascending=False).drop_duplicates(subset=['terms','lemma'], keep = 'first').sort_index()
+    print(df.head(5))
+    return df.to_json(orient='records')
+    # return jsonify(df.to_dict(orient='records'))
+
+
+if __name__ == '__main__':
+
+    app.run(debug=True)

ATEapi/model/term_extractor/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "EMBEDDIA/sloberta",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

ATEapi/model/term_extractor/special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

ATEapi/model/term_extractor/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "EMBEDDIA/sloberta",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

ATEapi/requirements.txt

@@ -0,0 +1,7 @@
+classla==1.1.0
+Flask==2.2.2
+lemmagen3==3.3.2
+numpy==1.21.6
+pandas==1.3.5
+torch
+transformers==4.20.1

ATEapi/temp_1.conllu

@@ -0,0 +1,789 @@
+# newpar id = 1
+# sent_id = 1.1
+# text = UNIVERZA V LJUBLJANI FAKULTETA ZA UPRAVO Magistrsko delo RAZVOJ VARSTVA PRAVIC ZAVEZANCEV V SLOVENSKEM DAVČNEM POSTOPKU Helena Truden Ljubljana, januar 2012 UNIVERZA V LJUBLJANI FAKULTETA ZA UPRAVO MAGISTRSKO DELO RAZVOJ VARSTVA PRAVIC ZAVEZANCEV V SLOVENSKEM DAVČNEM POSTOPKU Kandidatka: Helena Truden Vpisna številka: 04037934 Študijski program: magistrski študijski program Uprava druga stopnja Mentorica: doc. dr. Polonca Kovač Ljubljana, januar 2012 IZJAVA O AVTORSTVU MAGISTRSKEGA DELA Podpisana Helena Truden, študentka magistrskega študijskega programa Uprava druga stopnja, z vpisno številko 04037934, sem avtorica magistrskega dela z naslovom: Razvoj varstva pravic zavezancev v slovenskem davčnem postopku. S svojim podpisom zagotavljam, da: - je predloženo delo izključno rezultat mojega lastnega raziskovalnega dela, - sem poskrbela, da so dela in mnenja drugih avtorjev in avtoric, ki jih uporabljam v predloženem delu, navedena oz. citirana v skladu s fakultetnimi navodili, - sem poskrbela, da so vsa dela in mnenja drugih avtorjev oz. avtoric navedena v seznamu virov, ki je sestavni element predloženega dela in je zapisan v skladu s fakultetnimi navodili, - sem pridobila vsa dovoljenja za uporabo avtorskih del, ki so v celoti prenesena v predloženo delo in sem to tudi jasno zapisala v predloženem delu, - se zavedam, da je plagiatorstvo – predstavljanje tujih del, bodisi v obliki citata bodisi v obliki skoraj dobesednega parafraziranja bodisi v grafični obliki, s katerim so tuje misli oz. ideje predstavljene kot moje lastne – kaznivo po zakonu (Zakon o avtorski in sorodnih pravicah, Ur. list RS, št. 21/95), kršitev pa se sankcionira tudi z ukrepi po pravilih Univerze v Ljubljani in Fakultete za upravo, - se zavedam posledic, ki jih dokazano plagiatorstvo lahko predstavlja za predloženo delo in za moj status na Fakulteti za upravo, - je elektronska oblika identična s tiskano obliko magistrskega dela ter soglašam z objavo dela v zbirki »Dela FU«. Magistrsko delo je lektorirala: Martina Kočevar, učiteljica slovenskega jezika. Ljubljana, 16. 12. 2011 Podpis avtorice: POVZETEK Predmet raziskovanja magistrskega dela je razvoj varstva pravic zavezancev v slovenskem davčnem postopku.
+1	UNIVERZA	univerza	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+2	V	v	ADP	Sl	Case=Loc	_	_	_	_
+3	LJUBLJANI	Ljubljana	PROPN	Npfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+4	FAKULTETA	fakulteta	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+5	ZA	za	ADP	Sa	Case=Acc	_	_	_	_
+6	UPRAVO	uprava	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	_
+7	Magistrsko	magistrski	ADJ	Agpnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+8	delo	delo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+9	RAZVOJ	razvoj	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+10	VARSTVA	varstvo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+11	PRAVIC	pravica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+12	ZAVEZANCEV	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+13	V	v	ADP	Sl	Case=Loc	_	_	_	_
+14	SLOVENSKEM	slovenski	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+15	DAVČNEM	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+16	POSTOPKU	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+17	Helena	Helena	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+18	Truden	Truden	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+19	Ljubljana	Ljubljana	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+20	,	,	PUNCT	Z	_	_	_	_	_
+21	januar	januar	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+22	2012	2012	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+23	UNIVERZA	univerza	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+24	V	v	ADP	Sl	Case=Loc	_	_	_	_
+25	LJUBLJANI	Ljubljana	PROPN	Npfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+26	FAKULTETA	fakulteta	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+27	ZA	za	ADP	Sa	Case=Acc	_	_	_	_
+28	UPRAVO	uprava	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	_
+29	MAGISTRSKO	magistrski	ADJ	Agpnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+30	DELO	delo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+31	RAZVOJ	razvoj	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+32	VARSTVA	varstvo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+33	PRAVIC	pravica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+34	ZAVEZANCEV	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+35	V	v	ADP	Sl	Case=Loc	_	_	_	_
+36	SLOVENSKEM	slovenski	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+37	DAVČNEM	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+38	POSTOPKU	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+39	Kandidatka	kandidatka	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+40	:	:	PUNCT	Z	_	_	_	_	_
+41	Helena	Helena	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+42	Truden	Truden	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+43	Vpisna	vpisen	ADJ	Agpfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+44	številka	številka	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+45	:	:	PUNCT	Z	_	_	_	_	_
+46	04037934	04037934	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+47	Študijski	študijski	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+48	program	program	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+49	:	:	PUNCT	Z	_	_	_	_	_
+50	magistrski	magistrski	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+51	študijski	študijski	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+52	program	program	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+53	Uprava	uprava	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+54	druga	drug	ADJ	Mlpfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+55	stopnja	stopnja	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+56	Mentorica	mentorica	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+57	:	:	PUNCT	Z	_	_	_	_	_
+58	doc.	doc.	X	Y	Abbr=Yes	_	_	_	_
+59	dr.	dr.	X	Y	Abbr=Yes	_	_	_	_
+60	Polonca	Polonca	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+61	Kovač	Kovač	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+62	Ljubljana	Ljubljana	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+63	,	,	PUNCT	Z	_	_	_	_	_
+64	januar	januar	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+65	2012	2012	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+66	IZJAVA	izjava	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+67	O	o	ADP	Sl	Case=Loc	_	_	_	_
+68	AVTORSTVU	avtorstvo	NOUN	Ncnsl	Case=Loc|Gender=Neut|Number=Sing	_	_	_	_
+69	MAGISTRSKEGA	magistrski	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+70	DELA	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+71	Podpisana	podpisan	ADJ	Appfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+72	Helena	Helena	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+73	Truden	Truden	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+74	,	,	PUNCT	Z	_	_	_	_	_
+75	študentka	študentka	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+76	magistrskega	magistrski	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+77	študijskega	študijski	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+78	programa	program	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+79	Uprava	uprava	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+80	druga	drug	ADJ	Mlpfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+81	stopnja	stopnja	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+82	,	,	PUNCT	Z	_	_	_	_	_
+83	z	z	ADP	Si	Case=Ins	_	_	_	_
+84	vpisno	vpisen	ADJ	Agpfsi	Case=Ins|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+85	številko	številka	NOUN	Ncfsi	Case=Ins|Gender=Fem|Number=Sing	_	_	_	_
+86	04037934	04037934	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+87	,	,	PUNCT	Z	_	_	_	_	_
+88	sem	biti	AUX	Va-r1s-n	Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+89	avtorica	avtorica	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+90	magistrskega	magistrski	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+91	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+92	z	z	ADP	Si	Case=Ins	_	_	_	_
+93	naslovom	naslov	NOUN	Ncmsi	Case=Ins|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+94	:	:	PUNCT	Z	_	_	_	_	_
+95	Razvoj	razvoj	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+96	varstva	varstvo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+97	pravic	pravica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+98	zavezancev	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+99	v	v	ADP	Sl	Case=Loc	_	_	_	_
+100	slovenskem	slovenski	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+101	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+102	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+103	.	.	PUNCT	Z	_	_	_	_	_
+104	S	z	ADP	Si	Case=Ins	_	_	_	_
+105	svojim	svoj	DET	Px-msi	Case=Ins|Gender=Masc|Number=Sing|Poss=Yes|PronType=Prs|Reflex=Yes	_	_	_	_
+106	podpisom	podpis	NOUN	Ncmsi	Case=Ins|Gender=Masc|Number=Sing	_	_	_	_
+107	zagotavljam	zagotavljati	VERB	Vmpr1s	Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	SpaceAfter=No
+108	,	,	PUNCT	Z	_	_	_	_	_
+109	da	da	SCONJ	Cs	_	_	_	_	SpaceAfter=No
+110	:	:	PUNCT	Z	_	_	_	_	_
+111	-	-	PUNCT	Z	_	_	_	_	_
+112	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+113	predloženo	predložen	ADJ	Appnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+114	delo	delo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+115	izključno	izključno	ADV	Rgp	Degree=Pos	_	_	_	_
+116	rezultat	rezultat	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+117	mojega	moj	DET	Ps1nsgs	Case=Gen|Gender=Neut|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs	_	_	_	_
+118	lastnega	lasten	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+119	raziskovalnega	raziskovalen	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+120	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+121	,	,	PUNCT	Z	_	_	_	_	_
+122	-	-	PUNCT	Z	_	_	_	_	_
+123	sem	biti	AUX	Va-r1s-n	Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+124	poskrbela	poskrbeti	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+125	,	,	PUNCT	Z	_	_	_	_	_
+126	da	da	SCONJ	Cs	_	_	_	_	_
+127	so	biti	AUX	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+128	dela	delo	NOUN	Ncnpn	Case=Nom|Gender=Neut|Number=Plur	_	_	_	_
+129	in	in	CCONJ	Cc	_	_	_	_	_
+130	mnenja	mnenje	NOUN	Ncnpn	Case=Nom|Gender=Neut|Number=Plur	_	_	_	_
+131	drugih	drug	ADJ	Mlpmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+132	avtorjev	avtor	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+133	in	in	CCONJ	Cc	_	_	_	_	_
+134	avtoric	avtorica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+135	,	,	PUNCT	Z	_	_	_	_	_
+136	ki	ki	SCONJ	Cs	_	_	_	_	_
+137	jih	on	PRON	Pp3mpa--y	Case=Acc|Gender=Masc|Number=Plur|Person=3|PronType=Prs|Variant=Short	_	_	_	_
+138	uporabljam	uporabljati	VERB	Vmpr1s	Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	_
+139	v	v	ADP	Sl	Case=Loc	_	_	_	_
+140	predloženem	predložen	ADJ	Appmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+141	delu	del	NOUN	Ncmsl	Case=Loc|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+142	,	,	PUNCT	Z	_	_	_	_	_
+143	navedena	naveden	ADJ	Appfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+144	oz.	oz.	X	Y	Abbr=Yes	_	_	_	_
+145	citirana	citiran	ADJ	Appfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+146	v	v	ADP	Sl	Case=Loc	_	_	_	_
+147	skladu	sklad	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+148	s	z	ADP	Si	Case=Ins	_	_	_	_
+149	fakultetnimi	fakulteten	ADJ	Agpnpi	Case=Ins|Degree=Pos|Gender=Neut|Number=Plur	_	_	_	_
+150	navodili	navodilo	NOUN	Ncnpi	Case=Ins|Gender=Neut|Number=Plur	_	_	_	SpaceAfter=No
+151	,	,	PUNCT	Z	_	_	_	_	_
+152	-	-	PUNCT	Z	_	_	_	_	_
+153	sem	biti	AUX	Va-r1s-n	Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+154	poskrbela	poskrbeti	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+155	,	,	PUNCT	Z	_	_	_	_	_
+156	da	da	SCONJ	Cs	_	_	_	_	_
+157	so	biti	AUX	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+158	vsa	ves	DET	Pg-npn	Case=Nom|Gender=Neut|Number=Plur|PronType=Tot	_	_	_	_
+159	dela	delo	NOUN	Ncnpn	Case=Nom|Gender=Neut|Number=Plur	_	_	_	_
+160	in	in	CCONJ	Cc	_	_	_	_	_
+161	mnenja	mnenje	NOUN	Ncnpn	Case=Nom|Gender=Neut|Number=Plur	_	_	_	_
+162	drugih	drug	ADJ	Mlpmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+163	avtorjev	avtor	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+164	oz.	oz.	X	Y	Abbr=Yes	_	_	_	_
+165	avtoric	avtorica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+166	navedena	naveden	ADJ	Appnpn	Case=Nom|Degree=Pos|Gender=Neut|Number=Plur|VerbForm=Part	_	_	_	_
+167	v	v	ADP	Sl	Case=Loc	_	_	_	_
+168	seznamu	seznam	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+169	virov	vir	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+170	,	,	PUNCT	Z	_	_	_	_	_
+171	ki	ki	SCONJ	Cs	_	_	_	_	_
+172	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+173	sestavni	sestaven	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+174	element	element	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+175	predloženega	predložen	ADJ	Appnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+176	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+177	in	in	CCONJ	Cc	_	_	_	_	_
+178	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+179	zapisan	zapisan	ADJ	Appmsnn	Case=Nom|Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+180	v	v	ADP	Sl	Case=Loc	_	_	_	_
+181	skladu	sklad	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+182	s	z	ADP	Si	Case=Ins	_	_	_	_
+183	fakultetnimi	fakulteten	ADJ	Agpnpi	Case=Ins|Degree=Pos|Gender=Neut|Number=Plur	_	_	_	_
+184	navodili	navodilo	NOUN	Ncnpi	Case=Ins|Gender=Neut|Number=Plur	_	_	_	SpaceAfter=No
+185	,	,	PUNCT	Z	_	_	_	_	_
+186	-	-	PUNCT	Z	_	_	_	_	_
+187	sem	biti	AUX	Va-r1s-n	Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+188	pridobila	pridobiti	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+189	vsa	ves	DET	Pg-npa	Case=Acc|Gender=Neut|Number=Plur|PronType=Tot	_	_	_	_
+190	dovoljenja	dovoljenje	NOUN	Ncnpa	Case=Acc|Gender=Neut|Number=Plur	_	_	_	_
+191	za	za	ADP	Sa	Case=Acc	_	_	_	_
+192	uporabo	uporaba	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	_
+193	avtorskih	avtorski	ADJ	Agpnpg	Case=Gen|Degree=Pos|Gender=Neut|Number=Plur	_	_	_	_
+194	del	delo	NOUN	Ncnpg	Case=Gen|Gender=Neut|Number=Plur	_	_	_	SpaceAfter=No
+195	,	,	PUNCT	Z	_	_	_	_	_
+196	ki	ki	SCONJ	Cs	_	_	_	_	_
+197	so	biti	AUX	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+198	v	v	ADP	Sl	Case=Loc	_	_	_	_
+199	celoti	celota	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+200	prenesena	prenesen	ADJ	Appnpn	Case=Nom|Degree=Pos|Gender=Neut|Number=Plur|VerbForm=Part	_	_	_	_
+201	v	v	ADP	Sa	Case=Acc	_	_	_	_
+202	predloženo	predložen	ADJ	Appnsa	Case=Acc|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+203	delo	delo	NOUN	Ncnsa	Case=Acc|Gender=Neut|Number=Sing	_	_	_	_
+204	in	in	CCONJ	Cc	_	_	_	_	_
+205	sem	biti	AUX	Va-r1s-n	Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+206	to	ta	DET	Pd-nsa	Case=Acc|Gender=Neut|Number=Sing|PronType=Dem	_	_	_	_
+207	tudi	tudi	PART	Q	_	_	_	_	_
+208	jasno	jasno	ADV	Rgp	Degree=Pos	_	_	_	_
+209	zapisala	zapisati	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+210	v	v	ADP	Sl	Case=Loc	_	_	_	_
+211	predloženem	predložen	ADJ	Appmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+212	delu	delo	NOUN	Ncnsl	Case=Loc|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+213	,	,	PUNCT	Z	_	_	_	_	_
+214	-	-	PUNCT	Z	_	_	_	_	_
+215	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+216	zavedam	zavedati	VERB	Vmpr1s	Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	SpaceAfter=No
+217	,	,	PUNCT	Z	_	_	_	_	_
+218	da	da	SCONJ	Cs	_	_	_	_	_
+219	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+220	plagiatorstvo	plagiatorstvo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+221	–	–	PUNCT	Z	_	_	_	_	_
+222	predstavljanje	predstavljanje	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+223	tujih	tuj	ADJ	Agpnpg	Case=Gen|Degree=Pos|Gender=Neut|Number=Plur	_	_	_	_
+224	del	delo	NOUN	Ncnpg	Case=Gen|Gender=Neut|Number=Plur	_	_	_	SpaceAfter=No
+225	,	,	PUNCT	Z	_	_	_	_	_
+226	bodisi	bodisi	CCONJ	Cc	_	_	_	_	_
+227	v	v	ADP	Sl	Case=Loc	_	_	_	_
+228	obliki	oblika	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+229	citata	citat	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+230	bodisi	bodisi	CCONJ	Cc	_	_	_	_	_
+231	v	v	ADP	Sl	Case=Loc	_	_	_	_
+232	obliki	oblika	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+233	skoraj	skoraj	PART	Q	_	_	_	_	_
+234	dobesednega	dobeseden	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+235	parafraziranja	parafraziranje	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+236	bodisi	bodisi	CCONJ	Cc	_	_	_	_	_
+237	v	v	ADP	Sl	Case=Loc	_	_	_	_
+238	grafični	grafičen	ADJ	Agpfsl	Case=Loc|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+239	obliki	oblika	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+240	,	,	PUNCT	Z	_	_	_	_	_
+241	s	z	ADP	Si	Case=Ins	_	_	_	_
+242	katerim	kateri	DET	Pq-msi	Case=Ins|Gender=Masc|Number=Sing|PronType=Int	_	_	_	_
+243	so	biti	AUX	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+244	tuje	tuj	ADJ	Agpfpn	Case=Nom|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+245	misli	misel	NOUN	Ncfpn	Case=Nom|Gender=Fem|Number=Plur	_	_	_	_
+246	oz.	oz.	X	Y	Abbr=Yes	_	_	_	_
+247	ideje	ideja	NOUN	Ncfpn	Case=Nom|Gender=Fem|Number=Plur	_	_	_	_
+248	predstavljene	predstavljen	ADJ	Appfpn	Case=Nom|Degree=Pos|Gender=Fem|Number=Plur|VerbForm=Part	_	_	_	_
+249	kot	kot	SCONJ	Cs	_	_	_	_	_
+250	moje	moj	DET	Ps1fpns	Case=Nom|Gender=Fem|Number=Plur|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs	_	_	_	_
+251	lastne	lasten	ADJ	Agpfpn	Case=Nom|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+252	–	–	PUNCT	Z	_	_	_	_	_
+253	kaznivo	kazniv	ADJ	Agpnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+254	po	po	ADP	Sl	Case=Loc	_	_	_	_
+255	zakonu	zakon	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+256	(	(	PUNCT	Z	_	_	_	_	SpaceAfter=No
+257	Zakon	zakon	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+258	o	o	ADP	Sl	Case=Loc	_	_	_	_
+259	avtorski	avtorski	ADJ	Agpfsl	Case=Loc|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+260	in	in	CCONJ	Cc	_	_	_	_	_
+261	sorodnih	soroden	ADJ	Agpfpl	Case=Loc|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+262	pravicah	pravica	NOUN	Ncfpl	Case=Loc|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+263	,	,	PUNCT	Z	_	_	_	_	_
+264	Ur.	ur.	X	Y	Abbr=Yes	_	_	_	_
+265	list	list	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+266	RS	RS	PROPN	Npfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+267	,	,	PUNCT	Z	_	_	_	_	_
+268	št.	št.	X	Y	Abbr=Yes	_	_	_	_
+269	21	21	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+270	/	/	PUNCT	Z	_	_	_	_	SpaceAfter=No
+271	95	95	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+272	)	)	PUNCT	Z	_	_	_	_	SpaceAfter=No
+273	,	,	PUNCT	Z	_	_	_	_	_
+274	kršitev	kršitev	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+275	pa	pa	CCONJ	Cc	_	_	_	_	_
+276	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+277	sankcionira	sankcionirati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+278	tudi	tudi	PART	Q	_	_	_	_	_
+279	z	z	ADP	Si	Case=Ins	_	_	_	_
+280	ukrepi	ukrep	NOUN	Ncmpi	Case=Ins|Gender=Masc|Number=Plur	_	_	_	_
+281	po	po	ADP	Sl	Case=Loc	_	_	_	_
+282	pravilih	pravilo	NOUN	Ncnpl	Case=Loc|Gender=Neut|Number=Plur	_	_	_	_
+283	Univerze	univerza	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+284	v	v	ADP	Sl	Case=Loc	_	_	_	_
+285	Ljubljani	Ljubljana	PROPN	Npfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+286	in	in	CCONJ	Cc	_	_	_	_	_
+287	Fakultete	fakulteta	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+288	za	za	ADP	Sa	Case=Acc	_	_	_	_
+289	upravo	uprava	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+290	,	,	PUNCT	Z	_	_	_	_	_
+291	-	-	PUNCT	Z	_	_	_	_	_
+292	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+293	zavedam	zavedati	VERB	Vmpr1s	Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	_
+294	posledic	posledica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+295	,	,	PUNCT	Z	_	_	_	_	_
+296	ki	ki	SCONJ	Cs	_	_	_	_	_
+297	jih	on	PRON	Pp3mpa--y	Case=Acc|Gender=Masc|Number=Plur|Person=3|PronType=Prs|Variant=Short	_	_	_	_
+298	dokazano	dokazan	ADJ	Appnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+299	plagiatorstvo	plagiatorstvo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	_
+300	lahko	lahko	ADV	Rgp	Degree=Pos	_	_	_	_
+301	predstavlja	predstavljati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+302	za	za	ADP	Sa	Case=Acc	_	_	_	_
+303	predloženo	predložen	ADJ	Appnsa	Case=Acc|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+304	delo	delo	NOUN	Ncnsa	Case=Acc|Gender=Neut|Number=Sing	_	_	_	_
+305	in	in	CCONJ	Cc	_	_	_	_	_
+306	za	za	ADP	Sa	Case=Acc	_	_	_	_
+307	moj	moj	DET	Ps1msas	Case=Acc|Gender=Masc|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs	_	_	_	_
+308	status	status	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	_
+309	na	na	ADP	Sl	Case=Loc	_	_	_	_
+310	Fakulteti	fakulteta	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+311	za	za	ADP	Sa	Case=Acc	_	_	_	_
+312	upravo	uprava	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+313	,	,	PUNCT	Z	_	_	_	_	_
+314	-	-	PUNCT	Z	_	_	_	_	_
+315	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+316	elektronska	elektronski	ADJ	Agpfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+317	oblika	oblika	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+318	identična	identičen	ADJ	Agpfsn	Case=Nom|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+319	s	z	ADP	Si	Case=Ins	_	_	_	_
+320	tiskano	tiskan	ADJ	Appfsi	Case=Ins|Degree=Pos|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+321	obliko	oblika	NOUN	Ncfsi	Case=Ins|Gender=Fem|Number=Sing	_	_	_	_
+322	magistrskega	magistrski	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+323	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+324	ter	ter	CCONJ	Cc	_	_	_	_	_
+325	soglašam	soglašati	VERB	Vmpr1s	Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	_
+326	z	z	ADP	Si	Case=Ins	_	_	_	_
+327	objavo	objava	NOUN	Ncfsi	Case=Ins|Gender=Fem|Number=Sing	_	_	_	_
+328	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+329	v	v	ADP	Sl	Case=Loc	_	_	_	_
+330	zbirki	zbirka	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+331	»	»	PUNCT	Z	_	_	_	_	SpaceAfter=No
+332	Dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+333	FU	FU	PROPN	Npmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+334	«	«	PUNCT	Z	_	_	_	_	SpaceAfter=No
+335	.	.	PUNCT	Z	_	_	_	_	_
+336	Magistrsko	magistrski	ADJ	Agpnsa	Case=Acc|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+337	delo	delo	NOUN	Ncnsa	Case=Acc|Gender=Neut|Number=Sing	_	_	_	_
+338	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+339	lektorirala	lektorirati	VERB	Vmbp-sf	Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+340	:	:	PUNCT	Z	_	_	_	_	_
+341	Martina	Martina	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+342	Kočevar	Kočevar	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+343	,	,	PUNCT	Z	_	_	_	_	_
+344	učiteljica	učiteljica	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+345	slovenskega	slovenski	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+346	jezika	jezik	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+347	.	.	PUNCT	Z	_	_	_	_	_
+348	Ljubljana	Ljubljana	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+349	,	,	PUNCT	Z	_	_	_	_	_
+350	16.	16.	NUM	Mdo	NumForm=Digit|NumType=Ord	_	_	_	_
+351	12.	12.	NUM	Mdo	NumForm=Digit|NumType=Ord	_	_	_	_
+352	2011	2011	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+353	Podpis	podpis	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+354	avtorice	avtorica	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+355	:	:	PUNCT	Z	_	_	_	_	_
+356	POVZETEK	povzetek	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+357	Predmet	predmet	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+358	raziskovanja	raziskovanje	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+359	magistrskega	magistrski	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+360	dela	delo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+361	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+362	razvoj	razvoj	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+363	varstva	varstvo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+364	pravic	pravica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+365	zavezancev	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+366	v	v	ADP	Sl	Case=Loc	_	_	_	_
+367	slovenskem	slovenski	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+368	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+369	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+370	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.2
+# text = Davčni postopek je posebni upravni postopek, v katerem davčni organ odmeri višino davka, ki jo mora zavezanec plačati.
+1	Davčni	davčen	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+2	postopek	postopek	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+3	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+4	posebni	poseben	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+5	upravni	upraven	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+6	postopek	postopek	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+7	,	,	PUNCT	Z	_	_	_	_	_
+8	v	v	ADP	Sl	Case=Loc	_	_	_	_
+9	katerem	kateri	DET	Pq-msl	Case=Loc|Gender=Masc|Number=Sing|PronType=Int	_	_	_	_
+10	davčni	davčen	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+11	organ	organ	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+12	odmeri	odmeriti	VERB	Vmer3s	Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+13	višino	višina	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	_
+14	davka	davek	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+15	,	,	PUNCT	Z	_	_	_	_	_
+16	ki	ki	SCONJ	Cs	_	_	_	_	_
+17	jo	on	PRON	Pp3fsa--y	Case=Acc|Gender=Fem|Number=Sing|Person=3|PronType=Prs|Variant=Short	_	_	_	_
+18	mora	morati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+19	zavezanec	zavezanec	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+20	plačati	plačati	VERB	Vmen	Aspect=Perf|VerbForm=Inf	_	_	_	SpaceAfter=No
+21	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.3
+# text = V davčnem postopku prihaja do konflikta javnega in zasebnih interesov.
+1	V	v	ADP	Sl	Case=Loc	_	_	_	_
+2	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+3	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+4	prihaja	prihajati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+5	do	do	ADP	Sg	Case=Gen	_	_	_	_
+6	konflikta	konflikt	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+7	javnega	javen	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+8	in	in	CCONJ	Cc	_	_	_	_	_
+9	zasebnih	zaseben	ADJ	Agpmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+10	interesov	interes	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+11	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.4
+# text = Namen davčnega organa je namreč, da pobere čim višji znesek davka, interes zavezanca pa je, da je znesek davka, ki ga bo plačal, čim nižji.
+1	Namen	namen	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+2	davčnega	davčen	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+3	organa	organ	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+4	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+5	namreč	namreč	CCONJ	Cc	_	_	_	_	SpaceAfter=No
+6	,	,	PUNCT	Z	_	_	_	_	_
+7	da	da	SCONJ	Cs	_	_	_	_	_
+8	pobere	pobrati	VERB	Vmer3s	Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+9	čim	čim	ADV	Rgp	Degree=Pos	_	_	_	_
+10	višji	visok	ADJ	Agcmsay	Case=Acc|Definite=Def|Degree=Cmp|Gender=Masc|Number=Sing	_	_	_	_
+11	znesek	znesek	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	_
+12	davka	davek	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+13	,	,	PUNCT	Z	_	_	_	_	_
+14	interes	interes	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+15	zavezanca	zavezanec	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+16	pa	pa	CCONJ	Cc	_	_	_	_	_
+17	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	SpaceAfter=No
+18	,	,	PUNCT	Z	_	_	_	_	_
+19	da	da	SCONJ	Cs	_	_	_	_	_
+20	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+21	znesek	znesek	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+22	davka	davek	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+23	,	,	PUNCT	Z	_	_	_	_	_
+24	ki	ki	SCONJ	Cs	_	_	_	_	_
+25	ga	on	PRON	Pp3msa--y	Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs|Variant=Short	_	_	_	_
+26	bo	biti	AUX	Va-f3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Fut|VerbForm=Fin	_	_	_	_
+27	plačal	plačati	VERB	Vmep-sm	Aspect=Perf|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+28	,	,	PUNCT	Z	_	_	_	_	_
+29	čim	čim	ADV	Rgp	Degree=Pos	_	_	_	_
+30	nižji	nizek	ADJ	Agcmsny	Case=Nom|Definite=Def|Degree=Cmp|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+31	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.5
+# text = Kljub temu, da ima javni interes prednost pred interesi posameznikov, pa v davčnih postopkih pogosto prihaja do napak, zaradi katerih so kršene pravice zavezancev.
+1	Kljub	kljub	ADP	Sd	Case=Dat	_	_	_	_
+2	temu	ta	DET	Pd-nsd	Case=Dat|Gender=Neut|Number=Sing|PronType=Dem	_	_	_	SpaceAfter=No
+3	,	,	PUNCT	Z	_	_	_	_	_
+4	da	da	SCONJ	Cs	_	_	_	_	_
+5	ima	imeti	VERB	Vmpr3s-n	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+6	javni	javen	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+7	interes	interes	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+8	prednost	prednost	NOUN	Ncfsa	Case=Acc|Gender=Fem|Number=Sing	_	_	_	_
+9	pred	pred	ADP	Si	Case=Ins	_	_	_	_
+10	interesi	interes	NOUN	Ncmpi	Case=Ins|Gender=Masc|Number=Plur	_	_	_	_
+11	posameznikov	posameznik	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+12	,	,	PUNCT	Z	_	_	_	_	_
+13	pa	pa	CCONJ	Cc	_	_	_	_	_
+14	v	v	ADP	Sl	Case=Loc	_	_	_	_
+15	davčnih	davčen	ADJ	Agpmpl	Case=Loc|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+16	postopkih	postopek	NOUN	Ncmpl	Case=Loc|Gender=Masc|Number=Plur	_	_	_	_
+17	pogosto	pogosto	ADV	Rgp	Degree=Pos	_	_	_	_
+18	prihaja	prihajati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+19	do	do	ADP	Sg	Case=Gen	_	_	_	_
+20	napak	napaka	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+21	,	,	PUNCT	Z	_	_	_	_	_
+22	zaradi	zaradi	ADP	Sg	Case=Gen	_	_	_	_
+23	katerih	kateri	DET	Pq-fpg	Case=Gen|Gender=Masc|Number=Plur|PronType=Int	_	_	_	_
+24	so	biti	AUX	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+25	kršene	kršen	ADJ	Appfpn	Case=Nom|Degree=Pos|Gender=Fem|Number=Plur|VerbForm=Part	_	_	_	_
+26	pravice	pravica	NOUN	Ncfpn	Case=Nom|Gender=Fem|Number=Plur	_	_	_	_
+27	zavezancev	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+28	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.6
+# text = V teh primerih je pomembno, da zakon, ki ureja davčni postopek, ureja tudi pravice zavezancev na ta način, da s tem ni ogrožen javni interes. Zakon, ki ureja davčni postopek, je v Republiki Sloveniji od leta 1996 poseben Zakon o davčnem postopku, ki pa je eden od zakonov, ki se najpogosteje spreminja.
+1	V	v	ADP	Sl	Case=Loc	_	_	_	_
+2	teh	ta	DET	Pd-mpl	Case=Loc|Gender=Masc|Number=Plur|PronType=Dem	_	_	_	_
+3	primerih	primer	NOUN	Ncmpl	Case=Loc|Gender=Masc|Number=Plur	_	_	_	_
+4	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+5	pomembno	pomemben	ADJ	Agpnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+6	,	,	PUNCT	Z	_	_	_	_	_
+7	da	da	SCONJ	Cs	_	_	_	_	_
+8	zakon	zakon	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+9	,	,	PUNCT	Z	_	_	_	_	_
+10	ki	ki	SCONJ	Cs	_	_	_	_	_
+11	ureja	urejati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+12	davčni	davčen	ADJ	Agpmsay	Case=Acc|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+13	postopek	postopek	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+14	,	,	PUNCT	Z	_	_	_	_	_
+15	ureja	urejati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+16	tudi	tudi	PART	Q	_	_	_	_	_
+17	pravice	pravica	NOUN	Ncfpa	Case=Acc|Gender=Fem|Number=Plur	_	_	_	_
+18	zavezancev	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+19	na	na	ADP	Sa	Case=Acc	_	_	_	_
+20	ta	ta	DET	Pd-msa	Case=Acc|Gender=Masc|Number=Sing|PronType=Dem	_	_	_	_
+21	način	način	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+22	,	,	PUNCT	Z	_	_	_	_	_
+23	da	da	SCONJ	Cs	_	_	_	_	_
+24	s	z	ADP	Si	Case=Ins	_	_	_	_
+25	tem	ta	DET	Pd-nsi	Case=Ins|Gender=Neut|Number=Sing|PronType=Dem	_	_	_	_
+26	ni	biti	AUX	Va-r3s-y	Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin	_	_	_	_
+27	ogrožen	ogrožen	ADJ	Appmsnn	Case=Nom|Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+28	javni	javen	ADJ	Agpmsny	Case=Nom|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+29	interes	interes	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+30	.	.	PUNCT	Z	_	_	_	_	_
+31	Zakon	zakon	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+32	,	,	PUNCT	Z	_	_	_	_	_
+33	ki	ki	SCONJ	Cs	_	_	_	_	_
+34	ureja	urejati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+35	davčni	davčen	ADJ	Agpmsay	Case=Acc|Definite=Def|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+36	postopek	postopek	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+37	,	,	PUNCT	Z	_	_	_	_	_
+38	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+39	v	v	ADP	Sl	Case=Loc	_	_	_	_
+40	Republiki	republika	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+41	Sloveniji	Slovenija	PROPN	Npfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+42	od	od	ADP	Sg	Case=Gen	_	_	_	_
+43	leta	leto	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+44	1996	1996	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+45	poseben	poseben	ADJ	Agpmsnn	Case=Nom|Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+46	Zakon	zakon	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+47	o	o	ADP	Sl	Case=Loc	_	_	_	_
+48	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+49	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+50	,	,	PUNCT	Z	_	_	_	_	_
+51	ki	ki	SCONJ	Cs	_	_	_	_	_
+52	pa	pa	CCONJ	Cc	_	_	_	_	_
+53	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+54	eden	eden	NUM	Mlpmsn	Case=Nom|Gender=Masc|Number=Sing|NumForm=Word|NumType=Card	_	_	_	_
+55	od	od	ADP	Sg	Case=Gen	_	_	_	_
+56	zakonov	zakon	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+57	,	,	PUNCT	Z	_	_	_	_	_
+58	ki	ki	SCONJ	Cs	_	_	_	_	_
+59	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+60	najpogosteje	pogosto	ADV	Rgs	Degree=Sup	_	_	_	_
+61	spreminja	spreminjati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	SpaceAfter=No
+62	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.7
+# text = V 15 letih smo tako dobili kar tri nove Zakone o davčnem postopku, sedaj od leta 2007 velja ZDavP-2, ki pa je bil tudi že štirikrat noveliran.
+1	V	v	ADP	Sl	Case=Loc	_	_	_	_
+2	15	15	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+3	letih	leto	NOUN	Ncnpl	Case=Loc|Gender=Neut|Number=Plur	_	_	_	_
+4	smo	biti	AUX	Va-r1p-n	Mood=Ind|Number=Plur|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+5	tako	tako	ADV	Rgp	Degree=Pos	_	_	_	_
+6	dobili	dobiti	VERB	Vmep-pm	Aspect=Perf|Gender=Masc|Number=Plur|VerbForm=Part	_	_	_	_
+7	kar	kar	ADV	Rgp	Degree=Pos	_	_	_	_
+8	tri	trije	NUM	Mlcmpa	Case=Acc|Gender=Masc|Number=Plur|NumForm=Word|NumType=Card	_	_	_	_
+9	nove	nov	ADJ	Agpmpa	Case=Acc|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+10	Zakone	zakon	NOUN	Ncmpa	Case=Acc|Gender=Masc|Number=Plur	_	_	_	_
+11	o	o	ADP	Sl	Case=Loc	_	_	_	_
+12	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+13	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+14	,	,	PUNCT	Z	_	_	_	_	_
+15	sedaj	sedaj	ADV	Rgp	Degree=Pos	_	_	_	_
+16	od	od	ADP	Sg	Case=Gen	_	_	_	_
+17	leta	leto	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+18	2007	2007	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+19	velja	veljati	VERB	Vmpr3s	Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+20	ZDavP	ZDavP	PROPN	Npmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+21	-	-	PUNCT	Z	_	_	_	_	SpaceAfter=No
+22	2	2	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+23	,	,	PUNCT	Z	_	_	_	_	_
+24	ki	ki	SCONJ	Cs	_	_	_	_	_
+25	pa	pa	CCONJ	Cc	_	_	_	_	_
+26	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+27	bil	biti	AUX	Va-p-sm	Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+28	tudi	tudi	PART	Q	_	_	_	_	_
+29	že	že	PART	Q	_	_	_	_	_
+30	štirikrat	štirikrat	ADV	Rgp	Degree=Pos	_	_	_	_
+31	noveliran	noveliran	ADJ	Appmsnn	Case=Nom|Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+32	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.8
+# text = Pogosto so te spremembe ravno v smislu povečevanja pravic zavezancev, dodajajo pa se tudi instituti, ki zavezance spodbujajo k temu, da bi v čim večji meri in pravočasno poravnali svoje davčne obveznosti.
+1	Pogosto	pogosto	ADV	Rgp	Degree=Pos	_	_	_	_
+2	so	biti	VERB	Va-r3p-n	Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+3	te	ta	DET	Pd-fpn	Case=Nom|Gender=Fem|Number=Plur|PronType=Dem	_	_	_	_
+4	spremembe	sprememba	NOUN	Ncfpn	Case=Nom|Gender=Fem|Number=Plur	_	_	_	_
+5	ravno	ravno	PART	Q	_	_	_	_	_
+6	v	v	ADP	Sl	Case=Loc	_	_	_	_
+7	smislu	smisel	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+8	povečevanja	povečevanje	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+9	pravic	pravica	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+10	zavezancev	zavezanec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+11	,	,	PUNCT	Z	_	_	_	_	_
+12	dodajajo	dodajati	VERB	Vmpr3p	Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+13	pa	pa	CCONJ	Cc	_	_	_	_	_
+14	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+15	tudi	tudi	PART	Q	_	_	_	_	_
+16	instituti	institut	NOUN	Ncmpn	Case=Nom|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+17	,	,	PUNCT	Z	_	_	_	_	_
+18	ki	ki	SCONJ	Cs	_	_	_	_	_
+19	zavezance	zavezanec	NOUN	Ncmpa	Case=Acc|Gender=Masc|Number=Plur	_	_	_	_
+20	spodbujajo	spodbujati	VERB	Vmpr3p	Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+21	k	k	ADP	Sd	Case=Dat	_	_	_	_
+22	temu	ta	DET	Pd-nsd	Case=Dat|Gender=Neut|Number=Sing|PronType=Dem	_	_	_	SpaceAfter=No
+23	,	,	PUNCT	Z	_	_	_	_	_
+24	da	da	SCONJ	Cs	_	_	_	_	_
+25	bi	biti	AUX	Va-c	Mood=Cnd|VerbForm=Fin	_	_	_	_
+26	v	v	ADP	Sl	Case=Loc	_	_	_	_
+27	čim	čim	ADV	Rgp	Degree=Pos	_	_	_	_
+28	večji	velik	ADJ	Agcfsl	Case=Loc|Degree=Cmp|Gender=Fem|Number=Sing	_	_	_	_
+29	meri	mera	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+30	in	in	CCONJ	Cc	_	_	_	_	_
+31	pravočasno	pravočasno	ADV	Rgp	Degree=Pos	_	_	_	_
+32	poravnali	poravnati	VERB	Vmep-pm	Aspect=Perf|Gender=Masc|Number=Plur|VerbForm=Part	_	_	_	_
+33	svoje	svoj	DET	Px-fpa	Case=Acc|Gender=Fem|Number=Plur|Poss=Yes|PronType=Prs|Reflex=Yes	_	_	_	_
+34	davčne	davčen	ADJ	Agpfpa	Case=Acc|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+35	obveznosti	obveznost	NOUN	Ncfpa	Case=Acc|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+36	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.9
+# text = Poleg tega se nadrejeno uporabljajo procesne določbe področne zakonodaje EU in RS, podrejeno pa ZUP. K spremembam davčne zakonodaje pa je pripomoglo tudi dejstvo, da se tudi v Sloveniji spopadamo z gospodarsko krizo, ki je prizadela tudi zavezance.
+1	Poleg	poleg	ADP	Sg	Case=Gen	_	_	_	_
+2	tega	ta	DET	Pd-nsg	Case=Gen|Gender=Neut|Number=Sing|PronType=Dem	_	_	_	_
+3	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+4	nadrejeno	nadrejeno	ADV	Rgp	Degree=Pos	_	_	_	_
+5	uporabljajo	uporabljati	VERB	Vmpr3p	Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+6	procesne	procesen	ADJ	Agpfpn	Case=Nom|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+7	določbe	določba	NOUN	Ncfpn	Case=Nom|Gender=Fem|Number=Plur	_	_	_	_
+8	področne	področen	ADJ	Agpfsg	Case=Gen|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+9	zakonodaje	zakonodaja	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+10	EU	EU	PROPN	Npfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+11	in	in	CCONJ	Cc	_	_	_	_	_
+12	RS	RS	PROPN	Npfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+13	,	,	PUNCT	Z	_	_	_	_	_
+14	podrejeno	podrejen	ADJ	Appnsn	Case=Nom|Degree=Pos|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+15	pa	pa	CCONJ	Cc	_	_	_	_	_
+16	ZUP	ZUP	PROPN	Npfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+17	.	.	PUNCT	Z	_	_	_	_	_
+18	K	k	ADP	Sd	Case=Dat	_	_	_	_
+19	spremembam	sprememba	NOUN	Ncfpd	Case=Dat|Gender=Fem|Number=Plur	_	_	_	_
+20	davčne	davčen	ADJ	Agpfsg	Case=Gen|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+21	zakonodaje	zakonodaja	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+22	pa	pa	CCONJ	Cc	_	_	_	_	_
+23	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+24	pripomoglo	pripomoči	VERB	Vmep-sn	Aspect=Perf|Gender=Neut|Number=Sing|VerbForm=Part	_	_	_	_
+25	tudi	tudi	PART	Q	_	_	_	_	_
+26	dejstvo	dejstvo	NOUN	Ncnsn	Case=Nom|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+27	,	,	PUNCT	Z	_	_	_	_	_
+28	da	da	SCONJ	Cs	_	_	_	_	_
+29	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+30	tudi	tudi	PART	Q	_	_	_	_	_
+31	v	v	ADP	Sl	Case=Loc	_	_	_	_
+32	Sloveniji	Slovenija	PROPN	Npfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+33	spopadamo	spopadati	VERB	Vmpr1p	Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin	_	_	_	_
+34	z	z	ADP	Si	Case=Ins	_	_	_	_
+35	gospodarsko	gospodarski	ADJ	Agpfsi	Case=Ins|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+36	krizo	kriza	NOUN	Ncfsi	Case=Ins|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+37	,	,	PUNCT	Z	_	_	_	_	_
+38	ki	ki	SCONJ	Cs	_	_	_	_	_
+39	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+40	prizadela	prizadeti	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+41	tudi	tudi	PART	Q	_	_	_	_	_
+42	zavezance	zavezanec	NOUN	Ncmpa	Case=Acc|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+43	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.10
+# text = Mnogi zavezanci se soočajo s finančnimi težavami, zato se je Zakon o davčnem postopku ravno v luči gospodarske krize spremenil v tej smeri, da zavezancem olajša njihov položaj in jim omogoči več različnih možnosti za poplačilo davčnih obveznosti, predvsem z odlogi plačila in obročnim plačevanjem. Možnost odpisa, delnega odpisa, odloga in obročnega poplačila davčnih obveznosti se je od uvedbe prvega Zakona o davčnem postopku (1996) pa do danes povečala.
+1	Mnogi	mnog	DET	Pi-mpn	Case=Nom|Gender=Masc|Number=Plur|PronType=Ind	_	_	_	_
+2	zavezanci	zavezanec	NOUN	Ncmpn	Case=Nom|Gender=Masc|Number=Plur	_	_	_	_
+3	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+4	soočajo	soočati	VERB	Vmpr3p	Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+5	s	z	ADP	Si	Case=Ins	_	_	_	_
+6	finančnimi	finančen	ADJ	Agpfpi	Case=Ins|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+7	težavami	težava	NOUN	Ncfpi	Case=Ins|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+8	,	,	PUNCT	Z	_	_	_	_	_
+9	zato	zato	CCONJ	Cc	_	_	_	_	_
+10	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+11	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+12	Zakon	zakon	NOUN	Ncmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	_
+13	o	o	ADP	Sl	Case=Loc	_	_	_	_
+14	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+15	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+16	ravno	ravno	PART	Q	_	_	_	_	_
+17	v	v	ADP	Sl	Case=Loc	_	_	_	_
+18	luči	luč	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	_
+19	gospodarske	gospodarski	ADJ	Agpfsg	Case=Gen|Degree=Pos|Gender=Fem|Number=Sing	_	_	_	_
+20	krize	kriza	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+21	spremenil	spremeniti	VERB	Vmep-sm	Aspect=Perf|Gender=Masc|Number=Sing|VerbForm=Part	_	_	_	_
+22	v	v	ADP	Sl	Case=Loc	_	_	_	_
+23	tej	ta	DET	Pd-fsl	Case=Loc|Gender=Fem|Number=Sing|PronType=Dem	_	_	_	_
+24	smeri	smer	NOUN	Ncfsl	Case=Loc|Gender=Fem|Number=Sing	_	_	_	SpaceAfter=No
+25	,	,	PUNCT	Z	_	_	_	_	_
+26	da	da	SCONJ	Cs	_	_	_	_	_
+27	zavezancem	zavezanec	NOUN	Ncmpd	Case=Dat|Gender=Masc|Number=Plur	_	_	_	_
+28	olajša	olajšati	VERB	Vmer3s	Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+29	njihov	njihov	DET	Ps3msap	Case=Acc|Gender=Masc|Number=Sing|Number[psor]=Plur|Person=3|Poss=Yes|PronType=Prs	_	_	_	_
+30	položaj	položaj	NOUN	Ncmsan	Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing	_	_	_	_
+31	in	in	CCONJ	Cc	_	_	_	_	_
+32	jim	on	PRON	Pp3mpd--y	Case=Dat|Gender=Masc|Number=Plur|Person=3|PronType=Prs|Variant=Short	_	_	_	_
+33	omogoči	omogočiti	VERB	Vmer3s	Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	_	_	_	_
+34	več	več	DET	Rgc	PronType=Ind	_	_	_	_
+35	različnih	različen	ADJ	Agpfpg	Case=Gen|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+36	možnosti	možnost	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+37	za	za	ADP	Sa	Case=Acc	_	_	_	_
+38	poplačilo	poplačilo	NOUN	Ncnsa	Case=Acc|Gender=Neut|Number=Sing	_	_	_	_
+39	davčnih	davčen	ADJ	Agpfpg	Case=Gen|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+40	obveznosti	obveznost	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	SpaceAfter=No
+41	,	,	PUNCT	Z	_	_	_	_	_
+42	predvsem	predvsem	PART	Q	_	_	_	_	_
+43	z	z	ADP	Si	Case=Ins	_	_	_	_
+44	odlogi	odlog	NOUN	Ncmpi	Case=Ins|Gender=Masc|Number=Plur	_	_	_	_
+45	plačila	plačilo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+46	in	in	CCONJ	Cc	_	_	_	_	_
+47	obročnim	obročen	ADJ	Agpnsi	Case=Ins|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+48	plačevanjem	plačevanje	NOUN	Ncnsi	Case=Ins|Gender=Neut|Number=Sing	_	_	_	SpaceAfter=No
+49	.	.	PUNCT	Z	_	_	_	_	_
+50	Možnost	možnost	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+51	odpisa	odpis	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+52	,	,	PUNCT	Z	_	_	_	_	_
+53	delnega	delen	ADJ	Agpmsg	Case=Gen|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+54	odpisa	odpis	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+55	,	,	PUNCT	Z	_	_	_	_	_
+56	odloga	odlog	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+57	in	in	CCONJ	Cc	_	_	_	_	_
+58	obročnega	obročen	ADJ	Agpnsg	Case=Gen|Degree=Pos|Gender=Neut|Number=Sing	_	_	_	_
+59	poplačila	poplačilo	NOUN	Ncnsg	Case=Gen|Gender=Neut|Number=Sing	_	_	_	_
+60	davčnih	davčen	ADJ	Agpfpg	Case=Gen|Degree=Pos|Gender=Fem|Number=Plur	_	_	_	_
+61	obveznosti	obveznost	NOUN	Ncfpg	Case=Gen|Gender=Fem|Number=Plur	_	_	_	_
+62	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+63	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+64	od	od	ADP	Sg	Case=Gen	_	_	_	_
+65	uvedbe	uvedba	NOUN	Ncfsg	Case=Gen|Gender=Fem|Number=Sing	_	_	_	_
+66	prvega	prvi	ADJ	Mlomsg	Case=Gen|Gender=Masc|Number=Sing|NumType=Ord	_	_	_	_
+67	Zakona	zakon	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+68	o	o	ADP	Sl	Case=Loc	_	_	_	_
+69	davčnem	davčen	ADJ	Agpmsl	Case=Loc|Degree=Pos|Gender=Masc|Number=Sing	_	_	_	_
+70	postopku	postopek	NOUN	Ncmsl	Case=Loc|Gender=Masc|Number=Sing	_	_	_	_
+71	(	(	PUNCT	Z	_	_	_	_	SpaceAfter=No
+72	1996	1996	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+73	)	)	PUNCT	Z	_	_	_	_	_
+74	pa	pa	CCONJ	Cc	_	_	_	_	_
+75	do	do	ADP	Sg	Case=Gen	_	_	_	_
+76	danes	danes	ADV	Rgp	Degree=Pos	_	_	_	_
+77	povečala	povečati	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	SpaceAfter=No
+78	.	.	PUNCT	Z	_	_	_	_	_
+
+# sent_id = 1.11
+# text = Od prvotnih dovoljenih do 6 mesecev odloga oziroma največ do 6 mesečnih obrokov, se je možnost povečala na 12 mesecev odloga oziroma največ do 12 mesečnih obrokov (ZDavP-1), do 24 mesecev oziroma do največ 24 mesečnih obrokov.
+1	Od	od	ADP	Sg	Case=Gen	_	_	_	_
+2	prvotnih	prvoten	ADJ	Agpmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+3	dovoljenih	dovoljen	ADJ	Appmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur|VerbForm=Part	_	_	_	_
+4	do	do	ADP	Sg	Case=Gen	_	_	_	_
+5	6	6	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+6	mesecev	mesec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+7	odloga	odlog	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+8	oziroma	oziroma	CCONJ	Cc	_	_	_	_	_
+9	največ	največ	DET	Rgs	PronType=Ind	_	_	_	_
+10	do	do	ADP	Sg	Case=Gen	_	_	_	_
+11	6	6	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+12	mesečnih	mesečen	ADJ	Agpmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+13	obrokov	obrok	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+14	,	,	PUNCT	Z	_	_	_	_	_
+15	se	se	PRON	Px------y	PronType=Prs|Reflex=Yes|Variant=Short	_	_	_	_
+16	je	biti	AUX	Va-r3s-n	Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin	_	_	_	_
+17	možnost	možnost	NOUN	Ncfsn	Case=Nom|Gender=Fem|Number=Sing	_	_	_	_
+18	povečala	povečati	VERB	Vmep-sf	Aspect=Perf|Gender=Fem|Number=Sing|VerbForm=Part	_	_	_	_
+19	na	na	ADP	Sa	Case=Acc	_	_	_	_
+20	12	12	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+21	mesecev	mesec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+22	odloga	odlog	NOUN	Ncmsg	Case=Gen|Gender=Masc|Number=Sing	_	_	_	_
+23	oziroma	oziroma	CCONJ	Cc	_	_	_	_	_
+24	največ	največ	DET	Rgs	PronType=Ind	_	_	_	_
+25	do	do	ADP	Sg	Case=Gen	_	_	_	_
+26	12	12	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+27	mesečnih	mesečen	ADJ	Agpmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+28	obrokov	obrok	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+29	(	(	PUNCT	Z	_	_	_	_	SpaceAfter=No
+30	ZDavP	ZDavP	PROPN	Npmsn	Case=Nom|Gender=Masc|Number=Sing	_	_	_	SpaceAfter=No
+31	-	-	PUNCT	Z	_	_	_	_	SpaceAfter=No
+32	1	1	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	SpaceAfter=No
+33	)	)	PUNCT	Z	_	_	_	_	SpaceAfter=No
+34	,	,	PUNCT	Z	_	_	_	_	_
+35	do	do	ADP	Sg	Case=Gen	_	_	_	_
+36	24	24	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+37	mesecev	mesec	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	_
+38	oziroma	oziroma	CCONJ	Cc	_	_	_	_	_
+39	do	do	ADP	Sg	Case=Gen	_	_	_	_
+40	največ	največ	DET	Rgs	PronType=Ind	_	_	_	_
+41	24	24	NUM	Mdc	NumForm=Digit|NumType=Card	_	_	_	_
+42	mesečnih	mesečen	ADJ	Agpmpg	Case=Gen|Degree=Pos|Gender=Masc|Number=Plur	_	_	_	_
+43	obrokov	obrok	NOUN	Ncmpg	Case=Gen|Gender=Masc|Number=Plur	_	_	_	SpaceAfter=No
+44	.	.	PUNCT	Z	_	_	_	_	_

ATEapi/utils.py

@@ -0,0 +1,90 @@
+import os
+import glob
+import json
+import numpy as np
+import pandas as pd
+import warnings
+warnings.filterwarnings("ignore", category=FutureWarning)
+
+def read_conll(f, lowercase=True, max_example=None):
+    examples = []
+    # with open(in_file) as f:
+    word, lemma, pos, msd, label = [], [], [], [], []
+    for line in f.readlines():
+        sp = line.decode('utf-8').strip().split('\t')
+        # print(sp)
+        if len(sp) == 10:
+            if '-' not in sp[0]:
+                word.append(sp[1].lower() if lowercase else sp[1])
+                lemma.append(sp[2].lower() if lowercase else sp[2])
+                pos.append(sp[3])
+                msd.append(sp[4])
+                label.append('n')
+        elif len(word) > 0:
+            examples.append({'word': word, 'lemma': lemma, 'pos': pos, 'msd':msd,   'labels': label})
+            word, lemma, pos, msd, label = [], [], [], [], []
+            if (max_example is not None) and (len(examples) == max_example):
+                break
+    if len(word) > 0:
+        examples.append({'word': word, 'lemma': lemma, 'pos': pos,  'msd':msd, 'labels': label})
+    return pd.DataFrame(examples)
+
+
+def extract_terms_full(token_predictions,token_probabilities, val_texts, lemma_texts, pos_texts, msd_texts):
+    extracted_terms = list()
+    extracted_probs = list()
+    lemma_terms = list()
+    pos_terms = list()
+    msd_terms = list()
+    # go over all predictions
+    for i in range(len(token_predictions)):
+        pred = token_predictions[i]
+        prob = token_probabilities[i]
+        txt  = val_texts[i]
+        lemma  = lemma_texts[i]
+        pos  = pos_texts[i]
+        msd  = msd_texts[i]
+        for j in range(len(pred)):
+            if pred[j] == "B-T":
+                term = txt[j]
+                prob_term = str(round(prob[j][1],4))
+                lemma_term = lemma[j]
+                pos_term = pos[j]
+                msd_term = msd[j]
+                for k in range(j+1,len(pred)):
+                    if pred[k]=="T": 
+                        term+=" "+txt[k]
+                        prob_term+=" "+str(round(prob[k][2],4))
+                        lemma_term+=" "+ lemma[k]
+                        pos_term+=" "+ pos[k]
+                        msd_term+=" "+ msd[k]
+                    else: break
+                extracted_terms.append(term)
+                extracted_probs.append(prob_term)
+                lemma_terms.append(lemma_term)
+                pos_terms.append(pos_term)
+                msd_terms.append(msd_term)
+    return extracted_terms, extracted_probs, lemma_terms, pos_terms, msd_terms
+
+def remap(tokenizer, texts, preds, probs):
+    text = texts.split(' ')
+    len_token = []
+    res_pred = []
+    final_pred = []
+    res_prob = []
+    final_prob = []
+    for i in range(len(text)):
+        temp = len(tokenizer(text[i], add_special_tokens=False)['input_ids'])
+        len_token.append(temp)
+    for val in len_token:
+        res_pred.append(val)
+        res_pred.extend([0]*(val-1))    
+        res_prob.append(val)
+        res_prob.extend([0]*(val-1))  
+    for p1, p2 in zip(res_pred, preds[1:len(preds)-1]):
+        if p1 != 0:
+            final_pred.append(p2)
+    for p1, p2 in zip(res_prob, probs[1:len(probs)-1]):
+        if p1 != 0:
+            final_prob.append(p2)
+    return text, final_pred, final_prob

docker-compose.yml

@@ -1,19 +1,26 @@
 version: '3.1'
 services:
-    flask-serv:
-        build: .
-        restart: always
-        image: flask-server
-        ports:
-            - 8080:8080
-        volumes:  # when pushing to server, remove the first dot here in front of /mnt
-            - /mnt/ssd/ds_ftp/classla_OS2022:/usr/src/app/classla_OS2022
-            - ./swagger_server/classla/classla_resources:/root/classla_resources
-        environment:
-            - PYTHONUNBUFFERED=1
-    tika2:
-        image: apache/tika:1.28.4-full
-        entrypoint: [ "/bin/sh", "-c", "java -jar /tika-server-1.28.4.jar -h 0.0.0.0 -p 9999" ]
-        restart: always
-        ports:
-            - 9999:9999
+  flask-serv:
+    build: .
+    restart: always
+    image: flask-server
+    ports:
+      - "8080:8080"
+    volumes: # when pushing to server, remove the first dot here in front of /mnt
+      - /mnt/ssd/ds_ftp/classla_OS2022:/usr/src/app/classla_OS2022
+      - ./swagger_server/classla/classla_resources:/root/classla_resources
+    environment:
+      - PYTHONUNBUFFERED=1
+  tika2:
+    image: apache/tika:1.28.4-full
+    entrypoint: [ "/bin/sh", "-c", "java -jar /tika-server-1.28.4.jar -h 0.0.0.0 -p 9999" ]
+    restart: always
+    ports:
+      - "9999:9999"
+  ate-api:
+    build: ./ATEapi
+    restart: always
+    ports:
+      - "5000:5000"
+    volumes:
+      - ./swagger_server/classla/classla_resources:/home/appuser/classla_resources

swagger_server/controllers/extract_controller.py

@@ -1,6 +1,14 @@
 import connexion
-
+import json
+from pathlib import Path
 from swagger_server.models.izlusci_body import IzlusciBody  # noqa: E501
+from swagger_server.classla import cl_utils
+import requests
+
+# ATEapi_endpoint = "http://localhost:5000/predict"
+
+
+ATEapi_endpoint = "http://ate-api:5000/predict"
 
 
 def get_candidates(body):  # noqa: E501
@@ -16,6 +24,45 @@ def get_candidates(body):  # noqa: E501
     if connexion.request.is_json:
         body = IzlusciBody.from_dict(connexion.request.get_json())  # noqa: E501
 
+    # Todo: What is "conllus" in body input anyway??
+    # Todo: Kaj je s prepovedanimi besedami?
+    # file_ids = [10000, 10001, 10002, 10003]
+    # big_conllu = cl_utils.multipla_conllus_to_one_from_file_ids(file_ids)
+
+    # txt = Path('../ATEapi/temp_1.conllu').read_text('utf-8')  # LOCAL ONLY
+
+    # # Todo: does this close the file after the request?
+    # files = [
+    #     ('file', ('temp_1.conllu', open('../ATEapi/temp_1.conllu', 'rb'),
+    #               'application/octet-stream'))
+    # ]
+    # res = requests.post(ATEapi_endpoint, files=files)
+    # # res.status_code
+    # # res.text
+    #
+    # return res.text, res.status_code
+    #
+    # example_data = ""
+    # with open("C:\\Users\\Kiki\\Desktop\\Untitled-2.json", "r", encoding='utf-8') as f:
+    #     example_data = json.loads(f.read())
+    #
+    # d = 0
+    #
+    # ret = {'terminoloski_kandidati': [
+    #     {
+    #         'POSoznake': tk['msd'],
+    #         'kandidat': tk['terms'],  # more to bit lemma al terms?
+    #         'kanonicnaoblika': tk['canonical'],
+    #         'ranking': tk['ranking'],
+    #         'podporneutezi': [
+    #             6.0274563,  # ????????
+    #             6.0274563  # ??????
+    #         ],
+    #         'pogostostpojavljanja': [101, 71]  # ???????
+    #     }
+    #     for tk in example_data
+    # ]}
+
     data = {
         "terminoloski_kandidati": [
             {

swagger_server/controllers/jobs_controller.py

@@ -97,7 +97,7 @@ def try_do_jobs_classla():
                         [ex.submit(execute_classla_job, job) for job in unfinished_jobs]
 
         except Exception as e:
-            print(f"Exception in {__name__}: {e}")
+            print(f"Exception in try_do_jobs_classla")
         finally:
             time.sleep(3)
 
@@ -113,7 +113,7 @@ def try_do_jobs_doc2text():
                 with cf.ThreadPoolExecutor(max_workers=DOC2TEXT_CONCURANCE_LIMIT) as ex:
                     [ex.submit(execute_doc2text_job, job) for job in unfinished_jobs]
         except Exception as e:
-            print(f"Exception in {__name__}: {e}")
+            print(f"Exception in try_do_jobs_doc2text")
         finally:
             time.sleep(3)