Sequential lexicon enhanced bidirectional encoder representations from transformers: Chinese named entity recognition using sequential lexicon enhanced BERT.

ABSTRACT: Lexicon Enhanced Bidirectional Encoder Representations from Transformers (LEBERT) has achieved great success in Chinese Named Entity Recognition (NER). LEBERT performs lexical enhancement with a Lexicon Adapter layer, which facilitates deep lexicon knowledge fusion at the lower layers of BERT. However, this method is likely to introduce noise words and does not consider the possible conflicts between words when fusing lexicon information. To address this issue, we advocate for a novel lexical enhancement method, Sequential Lexicon Enhanced BERT (SLEBERT) for the Chinese NER, which builds sequential lexicon to reduce noise words and resolve the problem of lexical conflict. Compared with LEBERT, it leverages the position encoding of sequential lexicon and adaptive attention mechanism of sequ

SUBMITTER: Liu X 

PROVIDER: S-EPMC11622993 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature