dannashao
/

bert-base-uncased-finetuned-advanced-srl_arg

Token Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

dannashao commited on May 11

Commit

ecb5cb1

•

1 Parent(s): 1458291

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -30,6 +30,7 @@ It achieves the following results on the evaluation set:
 This more advanced SRL model uses similar apporach as the Augment method described in [NegBERT (Khandelwal, et al. 2020)](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.704.pdf).
 That is, adding a special token ([V]) immediately before the predicate:
 > This [V] is a sentence.
 Note that **the special token and the predicate is considered a whole**. That is, the actual sentence is like
 > 'This' **'[V] is'** 'a' 'sentence' '.'

 This more advanced SRL model uses similar apporach as the Augment method described in [NegBERT (Khandelwal, et al. 2020)](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.704.pdf).
 That is, adding a special token ([V]) immediately before the predicate:
 > This [V] is a sentence.
 Note that **the special token and the predicate is considered a whole**. That is, the actual sentence is like
 > 'This' **'[V] is'** 'a' 'sentence' '.'