Swapping same-type entities inside the training data, and training a second network on the augmented sentences, yields small, consistent gains on English NER and larger gains on a small cell-line corpus.
In: Proceedings of IJCAI 2019 (2019) 10 Zhu et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FlexNER: A Flexible LSTM-CNN Stack Framework for Named Entity Recognition
Swapping same-type entities inside the training data, and training a second network on the augmented sentences, yields small, consistent gains on English NER and larger gains on a small cell-line corpus.