Added other languages.

This commit is contained in:
Luka 2022-01-25 15:37:59 +01:00
parent f406ccc9fc
commit d81b8dd513
2 changed files with 144 additions and 12 deletions

View File

@ -3,20 +3,20 @@
## Description ## Description
This tool uses classla library as an API. It allows for calls on some preset classla settings, as well as a custom one. This tool uses classla library as an API. It allows for calls on some preset classla settings, as well as a custom one.
## Standard UD ## Slovenian Standard UD
Preset classla settings: Preset classla settings:
```json ```json
{ {
"lang": "sl", "lang": "sl",
"pos_lemma_pretag": false "pos_use_lexicon": true
} }
``` ```
Usage example: Usage example:
```commandline ```commandline
curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi."}' http://127.0.0.1:5000/standard-ud curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi."}' https://orodja.cjvt.si/oznacevalnik/standard-ud
``` ```
## Standard JOS ## Slovenian Standard JOS
Preset classla settings: Preset classla settings:
```json ```json
{ {
@ -27,24 +27,24 @@ Preset classla settings:
``` ```
Usage example: Usage example:
```commandline ```commandline
curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi."}' http://127.0.0.1:5000/standard-jos curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi."}' https://orodja.cjvt.si/oznacevalnik/standard-jos
``` ```
## Nonstandard UD ## Slovenian Nonstandard UD
Preset classla settings: Preset classla settings:
```json ```json
{ {
"lang": "sl", "lang": "sl",
"pos_use_lexicon": true, "pos_use_lexicon": true,
"type": "nonstandard_jos" "type": "nonstandard"
} }
``` ```
Usage example: Usage example:
```commandline ```commandline
curl -X POST -d '{"text": "kva smo mi zurali zadnje leto v zagrebu..."}' http://127.0.0.1:5000/nonstandard-ud curl -X POST -d '{"text": "kva smo mi zurali zadnje leto v zagrebu..."}' https://orodja.cjvt.si/oznacevalnik/nonstandard-ud
``` ```
## Nonstandard JOS ## Slovenian Nonstandard JOS
Preset classla settings: Preset classla settings:
```json ```json
{ {
@ -61,9 +61,85 @@ Preset classla settings:
``` ```
Usage example: Usage example:
```commandline ```commandline
curl -X POST -d '{"text": "kva smo mi zurali zadnje leto v zagrebu..."}' http://127.0.0.1:5000/nonstandard-jos curl -X POST -d '{"text": "kva smo mi zurali zadnje leto v zagrebu..."}' https://orodja.cjvt.si/oznacevalnik/nonstandard-jos
``` ```
## Croatian Standard UD
Preset classla settings:
```json
{
"lang": "hr",
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "Ante Starčević rođen je u Velikom Žitniku."}' https://orodja.cjvt.si/oznacevalnik/hr-standard-ud
```
## Croatian Nonstandard UD
Preset classla settings:
```json
{
"lang": "hr",
"type": "nonstandard"
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "kaj sam ja tulumaril jucer u ljubljani..."}' https://orodja.cjvt.si/oznacevalnik/hr-nonstandard-ud
```
## Serbian Standard UD
Preset classla settings:
```json
{
"lang": "sr",
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "Slobodan Jovanović rođen je u Novom Sadu."}' https://orodja.cjvt.si/oznacevalnik/sr-standard-ud
```
## Serbian Nonstandard UD
Preset classla settings:
```json
{
"lang": "sr",
"type": "nonstandard"
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "ne mogu da verujem kakvo je zezanje bilo prosle godine u zagrebu..."}' https://orodja.cjvt.si/oznacevalnik/sr-nonstandard-ud
```
## Bulgarian Standard UD
Preset classla settings:
```json
{
"lang": "bg",
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "Алеко Константинов е роден в Свищов."}' https://orodja.cjvt.si/oznacevalnik/bg-standard-ud
```
## Macedonian Standard UD
Preset classla settings:
```json
{
"lang": "mk",
}
```
Usage example:
```commandline
curl -X POST -d '{"text": "Крсте Петков Мисирков е роден во Постол."}' https://orodja.cjvt.si/oznacevalnik/mk-standard-ud
```
## Custom settings ## Custom settings
Custom settings may be used, however they have to be in compliance with what the library allows (you can check this on https://github.com/clarinsi/classla) Custom settings may be used, however they have to be in compliance with what the library allows (you can check this on https://github.com/clarinsi/classla)
@ -71,5 +147,5 @@ Custom settings may be used, however they have to be in compliance with what the
Usage example: Usage example:
```commandline ```commandline
curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi.", "settings": {"lang": "sl", "pos_lemma_pretag": false}}' http://127.0.0.1:5000/custom-settings curl -X POST -d '{"text": "France Prešeren je rojen v Vrbi.", "settings": {"lang": "sl", "pos_lemma_pretag": false}}' https://orodja.cjvt.si/oznacevalnik/custom-settings
``` ```

58
app.py
View File

@ -1,10 +1,17 @@
from flask import Flask, request from flask import Flask, request
import classla import classla
import gc import gc
import torch
classla.download('sl') classla.download('sl')
classla.download('sl', type='standard_jos') classla.download('sl', type='standard_jos')
classla.download('sl', type='nonstandard') classla.download('sl', type='nonstandard')
classla.download('hr')
classla.download('hr', type='nonstandard')
classla.download('sr')
classla.download('sr', type='nonstandard')
classla.download('mk')
classla.download('bg')
nlp_standard_UD = classla.Pipeline('sl', pos_use_lexicon=True) nlp_standard_UD = classla.Pipeline('sl', pos_use_lexicon=True)
nlp_standard_JOS = classla.Pipeline('sl', pos_use_lexicon=True, type='standard_jos') nlp_standard_JOS = classla.Pipeline('sl', pos_use_lexicon=True, type='standard_jos')
@ -16,6 +23,12 @@ nlp_nonstandard_JOS = classla.Pipeline('sl', processors={
"depparse": "standard_jos", "depparse": "standard_jos",
"ner": "nonstandard" "ner": "nonstandard"
}) })
nlp_hr_standard_UD = classla.Pipeline('hr')
nlp_hr_nonstandard_UD = classla.Pipeline('hr', type='nonstandard')
nlp_sr_standard_UD = classla.Pipeline('sr')
nlp_sr_nonstandard_UD = classla.Pipeline('sr', type='nonstandard')
nlp_bg_standard_UD = classla.Pipeline('bg')
nlp_mk_standard_UD = classla.Pipeline('mk')
app = Flask(__name__) app = Flask(__name__)
@ -30,10 +43,10 @@ def custom_settings():
if 'settings' in input_json: if 'settings' in input_json:
settings = input_json['settings'] settings = input_json['settings']
nlp = classla.Pipeline(**settings) nlp = classla.Pipeline(**settings)
# classla.Pipeline('sl', processors='tokenize,pos,lemma', pos_use_lexicon=True)
result = nlp(input_json['text']).to_conll() result = nlp(input_json['text']).to_conll()
del(nlp) del(nlp)
gc.collect() gc.collect()
torch.cuda.empty_cache()
else: else:
return f'ERROR `settings` were not given!' return f'ERROR `settings` were not given!'
return result return result
@ -67,5 +80,48 @@ def nonstandard_jos():
return doc.to_conll() return doc.to_conll()
@app.route('/hr-standard-ud', methods=["POST"])
def hr_standard_ud():
input_json = request.get_json(force=True)
doc = nlp_hr_standard_UD(input_json['text'])
return doc.to_conll()
@app.route('/hr-nonstandard-ud', methods=["POST"])
def hr_nonstandard_ud():
input_json = request.get_json(force=True)
doc = nlp_hr_nonstandard_UD(input_json['text'])
return doc.to_conll()
@app.route('/sr-standard-ud', methods=["POST"])
def sr_standard_ud():
input_json = request.get_json(force=True)
doc = nlp_sr_standard_UD(input_json['text'])
return doc.to_conll()
@app.route('/sr-nonstandard-ud', methods=["POST"])
def sr_nonstandard_ud():
input_json = request.get_json(force=True)
doc = nlp_sr_nonstandard_UD(input_json['text'])
return doc.to_conll()
@app.route('/bg-standard-ud', methods=["POST"])
def bg_standard_ud():
input_json = request.get_json(force=True)
doc = nlp_bg_standard_UD(input_json['text'])
return doc.to_conll()
@app.route('/mk-standard-ud', methods=["POST"])
def mk_standard_ud():
input_json = request.get_json(force=True)
doc = nlp_mk_standard_UD(input_json['text'])
return doc.to_conll()
if __name__ == '__main__': if __name__ == '__main__':
app.run(host="0.0.0.0") app.run(host="0.0.0.0")