srl taggin pipeline (output in .tsv)

This commit is contained in:
2019-02-24 22:23:32 +01:00
parent 9939bf0f55
commit b79721f6a7
25 changed files with 10104 additions and 4255 deletions

View File

@@ -81,43 +81,6 @@
81 akcijo akcija akcija N N _ Noun|common|feminine|singular|accusative 78 78 dol dol _ _ _ _ _ _ _ _
82 . . . . . _ . 0 0 modra modra _ _ _ _ _ _ _ _
1 Ker ker ker C C _ Conjunction|subordinating 14 14 vez vez _ _ _ _ _ _
2 se se se P P _ Pronoun|reflexive|+Clitic 14 14 del del _ _ _ _ _ _
3 nas jaz jaz P P _ Pronoun|personal|first|plural|accusative 5 5 dve dve _ _ _ _ _ _
4 v v v S S _ Adposition|locative 5 5 dol dol _ _ _ _ _ _
5 preteklosti preteklost preteklost N N _ Noun|common|feminine|singular|locative 14 14 štiri štiri _ _ TIME _ _ _
6 zaradi zaradi zaradi S S _ Adposition|genitive 8 8 dol dol _ _ _ _ _ _
7 genialnega genialen genialen A A _ Adjective|general|positive|masculine|singular|genitive 8 8 dol dol _ _ _ _ _ _
8 sistema sistem sistem N N _ Noun|common|masculine|singular|genitive 5 5 dol dol _ _ _ _ _ _
9 splošne splošen splošen A A _ Adjective|general|positive|feminine|singular|genitive 11 11 dol dol _ _ _ _ _ _
10 ljudske ljudski ljudski A A _ Adjective|general|positive|feminine|singular|genitive 11 11 dol dol _ _ _ _ _ _
11 obrambe obramba obramba N N _ Noun|common|feminine|singular|genitive 8 8 dol dol _ _ _ _ _ _
12 nihče nihče nihče P P _ Pronoun|negative|masculine|singular|nominative 14 14 ena ena _ _ ACT _ _ _
13 ni biti biti V V _ Verb|auxiliary|present|third|singular|+Negative 14 14 del del _ _ _ _ _ _
14 upal upati upati V V _ Verb|main|progressive|participle|singular|masculine 0 0 modra modra Y upati _ _ _ _
15 lotiti lotiti lotiti V V _ Verb|main|perfective|infinitive 14 14 dol dol Y lotiti MWPRED _ _ _
16 , , , , , _ , 0 0 modra modra _ _ _ _ _ _
17 se se se P P _ Pronoun|reflexive|+Clitic 20 20 del del _ _ _ _ _ _
18 sovrag sovrag sovrag N N _ Noun|common|masculine|singular|nominative 20 20 ena ena _ _ _ _ ACT _
19 sedaj sedaj sedaj R R _ Adverb|general|positive 20 20 štiri štiri _ _ _ _ TIME _
20 poslužuje posluževati posluževati V V _ Verb|main|progressive|present|third|singular 0 0 modra modra Y posluževati _ _ _ _
21 bolj bolj bolj R R _ Adverb|general|comparative 22 22 dol dol _ _ _ _ _ _
22 perfidnih perfiden perfiden A A _ Adjective|general|positive|feminine|plural|genitive 23 23 dol dol _ _ _ _ _ _
23 strategij strategija strategija N N _ Noun|common|feminine|plural|genitive 20 20 dve dve _ _ _ _ PAT _
24 , , , , , _ , 0 0 modra modra _ _ _ _ _ _
25 saj saj saj C C _ Conjunction|coordinating 30 30 vez vez _ _ _ _ _ _
26 nam jaz jaz P P _ Pronoun|personal|first|plural|dative 30 30 dve dve _ _ _ REC _ REC
27 lahko lahko lahko R R _ Adverb|general|positive 30 30 del del _ _ _ _ _ _
28 praktično praktično praktično R R _ Adverb|general|positive 29 29 dol dol _ _ _ _ _ _
29 kadarkoli kadarkoli kadarkoli R R _ Adverb|general|positive 30 30 tri tri _ _ _ _ _ MANN
30 odreže odrezati odrezati V V _ Verb|main|perfective|present|third|singular 0 0 modra modra Y odrezati _ _ _ _
31 dostop dostop dostop N N _ Noun|common|masculine|singular|accusative|-Animate 30 30 dve dve _ _ _ _ _ PAT
32 do do do S S _ Adposition|genitive 33 33 dol dol _ _ _ _ _ _
33 hrane hrana hrana N N _ Noun|common|feminine|singular|genitive 31 31 dol dol _ _ _ _ _ _
34 in in in C C _ Conjunction|coordinating 35 35 vez vez _ _ _ _ _ _
35 pijače pijača pijača N N _ Noun|common|feminine|singular|genitive 33 33 prir prir _ _ _ _ _ _
36 . . . . . _ . 0 0 modra modra _ _ _ _ _ _
1 Zadeva zadeva zadeva N N _ Noun|common|feminine|singular|nominative 2 2 ena ena _ _
2 je biti biti V V _ Verb|auxiliary|present|third|singular|-Negative 0 0 modra modra _ _
3 kristalno kristalno kristalno R R _ Adverb|general|positive 4 4 dol dol _ _
@@ -160,3 +123,40 @@
34 supersile supersila supersila N N _ Noun|common|feminine|singular|genitive 0 0 modra modra _ _ _ _
35 . . . . . _ . 0 0 modra modra _ _ _ _
1 Ker ker ker C C _ Conjunction|subordinating 14 14 vez vez _ _ _ _ _ _ _
2 se se se P P _ Pronoun|reflexive|+Clitic 14 14 del del _ _ _ _ _ _ _
3 nas jaz jaz P P _ Pronoun|personal|first|plural|accusative 5 5 dve dve _ _ _ _ _ _ _
4 v v v S S _ Adposition|locative 5 5 dol dol _ _ _ _ _ _ _
5 preteklosti preteklost preteklost N N _ Noun|common|feminine|singular|locative 14 14 štiri štiri _ _ _ TIME _ _ _
6 zaradi zaradi zaradi S S _ Adposition|genitive 8 8 dol dol _ _ _ _ _ _ _
7 genialnega genialen genialen A A _ Adjective|general|positive|masculine|singular|genitive 8 8 dol dol _ _ _ _ _ _ _
8 sistema sistem sistem N N _ Noun|common|masculine|singular|genitive 5 5 dol dol _ _ _ _ _ _ _
9 splošne splošen splošen A A _ Adjective|general|positive|feminine|singular|genitive 11 11 dol dol _ _ _ _ _ _ _
10 ljudske ljudski ljudski A A _ Adjective|general|positive|feminine|singular|genitive 11 11 dol dol _ _ _ _ _ _ _
11 obrambe obramba obramba N N _ Noun|common|feminine|singular|genitive 8 8 dol dol _ _ _ _ _ _ _
12 nihče nihče nihče P P _ Pronoun|negative|masculine|singular|nominative 14 14 ena ena _ _ _ ACT _ _ _
13 ni biti biti V V _ Verb|auxiliary|present|third|singular|+Negative 14 14 del del Y biti _ _ _ _ _
14 upal upati upati V V _ Verb|main|progressive|participle|singular|masculine 0 0 modra modra Y upati _ _ _ _ _
15 lotiti lotiti lotiti V V _ Verb|main|perfective|infinitive 14 14 dol dol Y lotiti _ MWPRED _ _ _
16 , , , , , _ , 0 0 modra modra _ _ _ _ _ _ _
17 se se se P P _ Pronoun|reflexive|+Clitic 20 20 del del _ _ _ _ _ _ _
18 sovrag sovrag sovrag N N _ Noun|common|masculine|singular|nominative 20 20 ena ena _ _ _ _ _ ACT _
19 sedaj sedaj sedaj R R _ Adverb|general|positive 20 20 štiri štiri _ _ _ _ _ TIME _
20 poslužuje posluževati posluževati V V _ Verb|main|progressive|present|third|singular 0 0 modra modra Y posluževati _ _ _ _ _
21 bolj bolj bolj R R _ Adverb|general|comparative 22 22 dol dol _ _ _ _ _ _ _
22 perfidnih perfiden perfiden A A _ Adjective|general|positive|feminine|plural|genitive 23 23 dol dol _ _ _ _ _ _ _
23 strategij strategija strategija N N _ Noun|common|feminine|plural|genitive 20 20 dve dve _ _ _ _ _ PAT _
24 , , , , , _ , 0 0 modra modra _ _ _ _ _ _ _
25 saj saj saj C C _ Conjunction|coordinating 30 30 vez vez _ _ _ _ _ _ _
26 nam jaz jaz P P _ Pronoun|personal|first|plural|dative 30 30 dve dve _ _ REC _ REC _ REC
27 lahko lahko lahko R R _ Adverb|general|positive 30 30 del del _ _ _ _ _ _ _
28 praktično praktično praktično R R _ Adverb|general|positive 29 29 dol dol _ _ _ _ _ _ _
29 kadarkoli kadarkoli kadarkoli R R _ Adverb|general|positive 30 30 tri tri _ _ _ _ _ _ MANN
30 odreže odrezati odrezati V V _ Verb|main|perfective|present|third|singular 0 0 modra modra Y odrezati _ _ _ _ _
31 dostop dostop dostop N N _ Noun|common|masculine|singular|accusative|-Animate 30 30 dve dve _ _ _ _ _ _ PAT
32 do do do S S _ Adposition|genitive 33 33 dol dol _ _ _ _ _ _ _
33 hrane hrana hrana N N _ Noun|common|feminine|singular|genitive 31 31 dol dol _ _ _ _ _ _ _
34 in in in C C _ Conjunction|coordinating 35 35 vez vez _ _ _ _ _ _ _
35 pijače pijača pijača N N _ Noun|common|feminine|singular|genitive 33 33 prir prir _ _ _ _ _ _ _
36 . . . . . _ . 0 0 modra modra _ _ _ _ _ _ _

View File

@@ -13,10 +13,11 @@
##################################################
# INPUT=./../../data/mate_train/sl.test.mate
INPUT=./../../data/kres_example_out/F0006347.xml.parsed.tsv
INPUT="$1"
Lang="ger"
MODEL="./srl-ger.model"
OUTPUT="${Lang}-eval.out"
# OUTPUT="${Lang}-eval.out"
OUTPUT="$2"
##################################################
## (2) These ones may need to be changed

25
tools/srl-20131216/tag_all.sh Executable file
View File

@@ -0,0 +1,25 @@
#!/bin/bash
IN_FOLDER="$1"
OUT_FOLDER="$2"
SUFFIX="srl.tsv"
mkdir -p $OUT_FOLDER
rm $OUT_FOLDER/*${SUFFIX}
for infile in $IN_FOLDER/*; do
echo "Tagging: ${infile}"
base=$(basename $infile | cut -d'.' -f1)
outfile=${OUT_FOLDER}/${base}.${SUFFIX}
# mate-tools tagger
./scripts/parse_srl_only_mod.sh $infile $outfile
if [ $? -eq 0 ]; then
echo "Saved as ${outfile}"
else
echo "ERR"
exit 1
fi
done