{"title":"Using word sense disambiguation for semantic role labeling","authors":"Wanxiang Che, Ting Liu","doi":"10.1109/IUCS.2010.5666646","DOIUrl":null,"url":null,"abstract":"Word sense disambiguation (WSD) is the process of identifying the correct meaning, or sense of a word in a given context. Semantic role labeling (SRL) aims at identifying the relations between predicates in a sentence and their associated arguments. They are two fundamental tasks in natural language processing to find a sentence-level semantic representation. To date, they have mostly been modeled in isolation. However, this approach neglects logical constraints between them. In this work, we present some novel word sense features for SRL and find that they can improve the performance significantly. Later, we exploit pipeline strategies which verify the automatic all word sense disambiguation could help the semantic role labeling and vice versa. We further propose a Markov logic model that jointly labels semantic roles and disambiguates all word senses. We show that this joint approach leads to a higher performance for WSD and SRL than those pipeline approaches.","PeriodicalId":108217,"journal":{"name":"2010 4th International Universal Communication Symposium","volume":"85 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 4th International Universal Communication Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IUCS.2010.5666646","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
Word sense disambiguation (WSD) is the process of identifying the correct meaning, or sense of a word in a given context. Semantic role labeling (SRL) aims at identifying the relations between predicates in a sentence and their associated arguments. They are two fundamental tasks in natural language processing to find a sentence-level semantic representation. To date, they have mostly been modeled in isolation. However, this approach neglects logical constraints between them. In this work, we present some novel word sense features for SRL and find that they can improve the performance significantly. Later, we exploit pipeline strategies which verify the automatic all word sense disambiguation could help the semantic role labeling and vice versa. We further propose a Markov logic model that jointly labels semantic roles and disambiguates all word senses. We show that this joint approach leads to a higher performance for WSD and SRL than those pipeline approaches.
词义消歧(WSD)是在给定的上下文中识别单词的正确含义或意义的过程。语义角色标注(Semantic role labeling, SRL)的目的是识别句子中谓语及其相关参数之间的关系。寻找句子级语义表示是自然语言处理中的两项基本任务。迄今为止,它们大多是单独建模的。然而,这种方法忽略了它们之间的逻辑约束。在这项工作中,我们提出了一些新的语义特征,并发现它们可以显着提高SRL的性能。随后,我们利用流水线策略验证了自动全词义消歧有助于语义角色标注,反之亦然。我们进一步提出了一个马尔可夫逻辑模型,该模型联合标记语义角色并消除所有词义的歧义。我们表明,这种联合方法比那些管道方法可以为WSD和SRL带来更高的性能。