{"title":"Combining Formal and Distributional Models of Temporal and Intensional Semantics","authors":"M. Lewis, Mark Steedman","doi":"10.3115/v1/W14-2406","DOIUrl":null,"url":null,"abstract":"We outline a vision for computational semantics in which formal compositional semantics is combined with a powerful, structured lexical semantics derived from distributional statistics. We consider how existing work (Lewis and Steedman, 2013) could be extended with a much richer lexical semantics using recent techniques for modelling processes (Scaria et al., 2013)—for example, learning that visiting events start with arriving and end with leaving. We show how to closely integrate this information with theories of formal semantics, allowing complex compositional inferences such as is visiting!has arrived in but will leave, which requires interpreting both the function and content words. This will allow machine reading systems to understand not just what has happened, but when.","PeriodicalId":107079,"journal":{"name":"Proceedings of the ACL 2014 Workshop on Semantic Parsing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ACL 2014 Workshop on Semantic Parsing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3115/v1/W14-2406","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11
Abstract
We outline a vision for computational semantics in which formal compositional semantics is combined with a powerful, structured lexical semantics derived from distributional statistics. We consider how existing work (Lewis and Steedman, 2013) could be extended with a much richer lexical semantics using recent techniques for modelling processes (Scaria et al., 2013)—for example, learning that visiting events start with arriving and end with leaving. We show how to closely integrate this information with theories of formal semantics, allowing complex compositional inferences such as is visiting!has arrived in but will leave, which requires interpreting both the function and content words. This will allow machine reading systems to understand not just what has happened, but when.
我们概述了计算语义的愿景,其中形式组合语义与源自分布统计的强大结构化词汇语义相结合。我们考虑如何使用最新的建模过程技术(Scaria et al., 2013)用更丰富的词汇语义扩展现有的工作(Lewis and Steedman, 2013) -例如,学习访问事件从到达开始,以离开结束。我们展示了如何将这些信息与形式语义理论紧密集成,从而允许复杂的组合推理,例如正在访问!已经到达但即将离开,这需要同时解释功能词和实义词。这将使机器阅读系统不仅能了解发生了什么,还能了解发生的时间。