SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

NER: Add new WNUT’17 example (#4681)

Browse Source 
* ner: add preprocessing script for examples that splits longer sentences

* ner: example shell scripts use local preprocessing now

* ner: add new example section for WNUT’17 NER task. Remove old English CoNLL-03 results

* ner: satisfy black and isort
This commit is contained in:
Stefan Schweter
2020-06-05 01:13:17 +02:00
committed by GitHub
parent 0e1869cc28
commit 2a4b9e09c0
4 changed files with 167 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/token-classification/run_pl.sh
View File

@@ -11,12 +11,12 @@ curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-dev.tsv?attre
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > dev.txt.tmp
curl -L 'https://sites.google.com/site/germeval2014ner/data/NER-de-test.tsv?attredirects=0&d=1' \
| grep -v "^#" | cut -f 2,3 | tr '\t' ' ' > test.txt.tmp
wget "https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py"
export MAX_LENGTH=128
export BERT_MODEL=bert-base-multilingual-cased
python3 preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt
python3 preprocess.py dev.txt.tmp $BERT_MODEL $MAX_LENGTH > dev.txt
python3 preprocess.py test.txt.tmp $BERT_MODEL $MAX_LENGTH > test.txt
python3 scripts/preprocess.py train.txt.tmp $BERT_MODEL $MAX_LENGTH > train.txt
python3 scripts/preprocess.py dev.txt.tmp $BERT_MODEL $MAX_LENGTH > dev.txt
python3 scripts/preprocess.py test.txt.tmp $BERT_MODEL $MAX_LENGTH > test.txt
cat train.txt dev.txt test.txt | cut -d " " -f 2 | grep -v "^$"| sort | uniq > labels.txt
export BATCH_SIZE=32
export NUM_EPOCHS=3