Unified Lattice Graph Fusion for Chinese Named Entity Recognition
This work addresses the challenge of improving named entity recognition in Chinese, a domain-specific task, by enhancing semantic integration, though it appears incremental as it builds on prior lattice-based methods.
The paper tackles the problem of integrating lexicon information into character-level Chinese named entity recognition by proposing a Unified Lattice Graph Fusion approach, which captures semantic and boundary relations across units and includes an auxiliary lexicon entity classification task, achieving superior results on four benchmark datasets.
Integrating lexicon into character-level sequence has been proven effective to leverage word boundary and semantic information in Chinese named entity recognition (NER). However, prior approaches usually utilize feature weighting and position coupling to integrate word information, but ignore the semantic and contextual correspondence between the fine-grained semantic units in the character-word space. To solve this issue, we propose a Unified Lattice Graph Fusion (ULGF) approach for Chinese NER. ULGF can explicitly capture various semantic and boundary relations across different semantic units with the adjacency matrix by converting the lattice structure into a unified graph. We stack multiple graph-based intra-source self-attention and inter-source cross-gating fusion layers that iteratively carry out semantic interactions to learn node representations. To alleviate the over-reliance on word information, we further propose to leverage lexicon entity classification as an auxiliary task. Experiments on four Chinese NER benchmark datasets demonstrate the superiority of our ULGF approach.