Findings of the Association for Computational Linguistics: EMNLP 2021最新文献

筛选

英文中文

Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing 基于语义-结构对齐的无监督领域自适应依赖分析方法

Findings of the Association for Computational Linguistics: EMNLP 2021 Pub Date : 1900-01-01 DOI: 10.18653/v1/2021.findings-emnlp.186

Boda Lin, Mingzheng Li, Si Li, Yong Luo

{"title":"Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing","authors":"Boda Lin, Mingzheng Li, Si Li, Yong Luo","doi":"10.18653/v1/2021.findings-emnlp.186","DOIUrl":"https://doi.org/10.18653/v1/2021.findings-emnlp.186","url":null,"abstract":"Unsupervised cross-domain dependency parsing is to accomplish domain adaptation for dependency parsing without using labeled data in target domain. Existing methods are often of the pseudo-annotation type, which generates data through self-annotation of the base model and performing iterative training. However, these methods fail to consider the change of model structure for domain adaptation. In addition, the structural information contained in the text cannot be fully exploited. To remedy these drawbacks, we propose a Semantics-Structure Adaptative Dependency Parser (SSADP), which accomplishes unsupervised cross-domain dependency parsing without relying on pseudo-annotation or data selection. In particular, we design two feature extractors to extract semantic and structural features respectively. For each type of features, a corresponding feature adaptation method is utilized to achieve domain adaptation to align the domain distribution, which effectively enhances the unsupervised crossdomain transfer capability of the model. We validate the effectiveness of our model by conducting experiments on the CODT1 and CTB9 respectively, and the results demonstrate that our model can achieve consistent performance improvement. Besides, we verify the structure transfer ability of the proposed model by introducing Weisfeiler-Lehman Test.","PeriodicalId":373905,"journal":{"name":"Findings of the Association for Computational Linguistics: EMNLP 2021","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125775215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2