However, recent outstanding studies are limited by the small-scale annotated corpus. Existing methods have already achieved high performance on several benchmarks (e.g., Bakeoff-2005).
Due to the development of pre-trained language models (PLM), pre-trained knowledge can help neural methods solve the main problems of the CWS in significant measure. Thus, Chinese word segmentation (CWS) is a fundamental task in NLP. Precise information of word boundary can alleviate the problem of lexical ambiguity to improve the performance of natural language processing (NLP) tasks. Lexicon-Based Graph Convolutional Network for Chinese Word Segmentationįindings of the Association for Computational Linguistics: EMNLP 2021Īssociation for Computational Linguistics Further experiments and analyses demonstrate that our proposed framework effectively models the lexicon to enhance the ability of basic neural frameworks and strengthens the robustness in the cross-domain scenario.", Experimental results on five benchmarks and four cross-domain datasets show the lexicon-based graph convolutional network successfully captures the information of candidate words and helps to improve performance on the benchmarks (Bakeoff-2005 and CTB6) and the cross-domain datasets (SIGHAN-2010). To further improve the performance of CWS methods based on fine-tuning the PLMs, we propose a novel neural framework, LBGCN, which incorporates a lexicon-based graph convolutional network into the Transformer encoder. Publisher = "Association for Computational Linguistics",ĭoi = "10.18653/v1/2021.findings-emnlp.248",Ībstract = "Precise information of word boundary can alleviate the problem of lexical ambiguity to improve the performance of natural language processing (NLP) tasks.
#Huang jing xiang videos mods#
Cite (Informal): Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation (Huang et al., Findings 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Software:Ģ.zip Video: = "Lexicon-Based Graph Convolutional Network for hinese Word Segmentation",īooktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",Īddress = "Punta Cana, Dominican Republic", Association for Computational Linguistics. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2908–2917, Punta Cana, Dominican Republic. Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation. Anthology ID: 2021.findings-emnlp.248 Volume: Findings of the Association for Computational Linguistics: EMNLP 2021 Month: November Year: 2021 Address: Punta Cana, Dominican Republic Venue: Findings SIG: SIGDAT Publisher: Association for Computational Linguistics Note: Pages: 2908–2917 Language: URL: DOI: 10.18653/v1/2021.findings-emnlp.248 Bibkey: huang-etal-2021-lexicon-based Cite (ACL): Kaiyu Huang, Hao Yu, Junpeng Liu, Wei Liu, Jingxiang Cao, and Degen Huang. Further experiments and analyses demonstrate that our proposed framework effectively models the lexicon to enhance the ability of basic neural frameworks and strengthens the robustness in the cross-domain scenario.
Abstract Precise information of word boundary can alleviate the problem of lexical ambiguity to improve the performance of natural language processing (NLP) tasks.
0 kommentar(er)
