Multiple Character Embeddings for Chinese Word Segmentation
원문 초록
Chinese word segmentation (CWS) is often regarded as a character-based sequence labeling task in most current works which have achieved great success with the help of powerful neural networks. However, these works neglect an important clue: Chinese characters incorporate both semantic and phonetic meanings. In this paper, we introduce multiple character embeddings including Pinyin Romanization and Wubi Input, both of which are easily accessible and effective in depicting semantics of characters. We propose a novel shared Bi-LSTM-CRF model to fuse linguistic features efficiently by sharing the LSTM network during the training procedure. Extensive experiments on five corpora show that extra embeddings help obtain a significant improvement in labeling accuracy. Specifically, we achieve the state-of-the-art performance in AS and CityU corpora with F1 scores of 96.9 and 97.3, respectively without leveraging any external lexical resources.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation
Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model
The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS
Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.