基于形态学的屈折语言模型

Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems Pub Date : 2011-11-10 DOI:10.1109/IDAACS.2011.6072829

Tomas Brychcin, Miloslav Konopík

{"title":"基于形态学的屈折语言模型","authors":"Tomas Brychcin, Miloslav Konopík","doi":"10.1109/IDAACS.2011.6072829","DOIUrl":null,"url":null,"abstract":"This paper shows a method to improve the language modeling for inflectional languages such as the Czech and Slovak language. Methods are based upon the principle of class-based language models, where word classes are derived from morphological information. Our experiments show that the linear interpolation with the class-based language models outperforms the stand-alone word N-gram language model about 10–30%.","PeriodicalId":106306,"journal":{"name":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"Morphological based language models for inflectional languages\",\"authors\":\"Tomas Brychcin, Miloslav Konopík\",\"doi\":\"10.1109/IDAACS.2011.6072829\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper shows a method to improve the language modeling for inflectional languages such as the Czech and Slovak language. Methods are based upon the principle of class-based language models, where word classes are derived from morphological information. Our experiments show that the linear interpolation with the class-based language models outperforms the stand-alone word N-gram language model about 10–30%.\",\"PeriodicalId\":106306,\"journal\":{\"name\":\"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems\",\"volume\":\"17 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-11-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IDAACS.2011.6072829\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IDAACS.2011.6072829","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 12

摘要

本文提出了一种改进捷克语、斯洛伐克语等屈折变形语言的语言建模方法。方法基于基于类的语言模型的原则，其中词类派生自形态学信息。我们的实验表明，基于类的语言模型的线性插值比独立的单词N-gram语言模型要好10-30%。

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

Morphological based language models for inflectional languages

This paper shows a method to improve the language modeling for inflectional languages such as the Czech and Slovak language. Methods are based upon the principle of class-based language models, where word classes are derived from morphological information. Our experiments show that the linear interpolation with the class-based language models outperforms the stand-alone word N-gram language model about 10–30%.

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

Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems

自引率

0.00%

发文量