Self-attention networks achieve competitive results to BiLSTM-CRF on Chinese word segmentation, with BERT and word integration yielding the best reported performance on six heterogeneous domain benchmarks.
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Process- ing, pages 4902–4908
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Investigating Self-Attention Network for Chinese Word Segmentation
Self-attention networks achieve competitive results to BiLSTM-CRF on Chinese word segmentation, with BERT and word integration yielding the best reported performance on six heterogeneous domain benchmarks.