paper-with-me

홈 › Papers

Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning

2019-03-11 · Weipeng Huang, Xingyi Cheng, Kunlong Chen, Taifeng Wang, Wei Chu

The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage their common underlying knowledge. In this paper, we propose a domain adaptive segmenter to exploit diverse criteria of various datasets. Our model is based on Bidirectional Encoder Representations from Transformers (BERT), which is responsible for introducing open-domain knowledge. Private and shared projection layers are proposed to capture domain-specific knowledge and common knowledge, respectively. We also optimize computational efficiency via distillation, quantization, and compiler optimization. Experiments show that our segmenter outperforms the previous state of the art (SOTA) models on 10 CWS datasets with superior efficiency.

📄 PDF Abstract BibTeX arXiv:1903.04190

Code (0)

등록된 구현이 없습니다.

Tasks

Chinese Word SegmentationCompiler OptimizationComputational EfficiencyQuantizationSegmentation

Similar Papers 제목 키워드 기반

Fast and Accurate Neural Word Segmentation for Chinese

2017-04-24 · ACL 2017 7 · Deng Cai, Hai Zhao, Zhisong Zhang, Yuan Xin 외

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neu…

Chinese Word SegmentationFeature EngineeringSegmentation

Towards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning

2020-12-01 · COLING 2020 8 · Weipeng Huang, Xingyi Cheng, Kunlong Chen, Taifeng Wang 외

The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datase…

Chinese Word SegmentationCompiler OptimizationComputational EfficiencyQuantization+1

A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection

2020-01-03 · Pei Xu, Shan Huang, Hongzhen Wang, Hao Song 외

Chinese keyword spotting is a challenging task as there is no visual blank for Chinese words. Different from English words which are split naturally by visual blanks, Chinese words are generally split only by semantic in…

Keyword SpottingLine Detection

A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing

2019-04-09 · TACL 2020 1 · Hang Yan, Xipeng Qiu, Xuanjing Huang

Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on word-level. Therefore word segmentation is the precondition of depe…

Chinese Word SegmentationDependency ParsingFeature EngineeringLanguage Modeling+2

Attention Is All You Need for Chinese Word Segmentation

2019-10-31 · EMNLP 2020 11 · Sufeng Duan, Hai Zhao

Taking greedy decoding algorithm as it should be, this work focuses on further strengthening the model itself for Chinese word segmentation (CWS), which results in an even more fast and more accurate CWS model. Our model…

AllChinese Word SegmentationDecoderSegmentation