连续词表示的词法句法规律:多语言研究。

VS@HLT-NAACL Pub Date : 2015-06-01 DOI:10.3115/v1/W15-1518

Garrett Nicolai, Colin Cherry, Grzegorz Kondrak

{"title":"连续词表示的词法句法规律:多语言研究。","authors":"Garrett Nicolai, Colin Cherry, Grzegorz Kondrak","doi":"10.3115/v1/W15-1518","DOIUrl":null,"url":null,"abstract":"We replicate the syntactic experiments of Mikolov et al. (2013b) on English, and expand them to include morphologically complex languages. We learn vector representations for Dutch, French, German, and Spanish with the WORD2VEC tool, and investigate to what extent inflectional information is preserved across vectors. We observe that the accuracy of vectors on a set of syntactic analogies is inversely correlated with the morphological complexity of the language.","PeriodicalId":299646,"journal":{"name":"VS@HLT-NAACL","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Morpho-syntactic Regularities in Continuous Word Representations: A multilingual study.\",\"authors\":\"Garrett Nicolai, Colin Cherry, Grzegorz Kondrak\",\"doi\":\"10.3115/v1/W15-1518\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We replicate the syntactic experiments of Mikolov et al. (2013b) on English, and expand them to include morphologically complex languages. We learn vector representations for Dutch, French, German, and Spanish with the WORD2VEC tool, and investigate to what extent inflectional information is preserved across vectors. We observe that the accuracy of vectors on a set of syntactic analogies is inversely correlated with the morphological complexity of the language.\",\"PeriodicalId\":299646,\"journal\":{\"name\":\"VS@HLT-NAACL\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"VS@HLT-NAACL\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3115/v1/W15-1518\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"VS@HLT-NAACL","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3115/v1/W15-1518","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

摘要

我们复制了Mikolov等人(2013b)在英语上的句法实验，并将其扩展到包括形态复杂的语言。我们使用WORD2VEC工具学习荷兰语、法语、德语和西班牙语的向量表示，并研究跨向量保留屈折信息的程度。我们观察到，在一组句法类比上向量的准确性与语言的形态复杂性呈负相关。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Morpho-syntactic Regularities in Continuous Word Representations: A multilingual study.

We replicate the syntactic experiments of Mikolov et al. (2013b) on English, and expand them to include morphologically complex languages. We learn vector representations for Dutch, French, German, and Spanish with the WORD2VEC tool, and investigate to what extent inflectional information is preserved across vectors. We observe that the accuracy of vectors on a set of syntactic analogies is inversely correlated with the morphological complexity of the language.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

VS@HLT-NAACL

自引率

0.00%

发文量

期刊最新文献

Distributional Semantic Concept Models for Entity Relation Discovery Learning Distributed Representations for Multilingual Text Sequences Vector Space Models for Scientific Document Summarization A Deep Architecture for Non-Projective Dependency Parsing Dependency Link Embeddings: Continuous Representations of Syntactic Substructures