面向SMT的广义依赖树语言模型

Q4 Computer Science

Journal of Information Processing Pub Date : 2016-06-15 DOI:10.5715/JNLP.23.299

John Richardson, Taku Kudo, H. Kazawa, S. Kurohashi

{"title":"面向SMT的广义依赖树语言模型","authors":"John Richardson, Taku Kudo, H. Kazawa, S. Kurohashi","doi":"10.5715/JNLP.23.299","DOIUrl":null,"url":null,"abstract":"In this paper we describe a generalized dependency tree language model for machine translation. We consider in detail the question of how to define tree-based n-grams, or ‘t-treelets’, and thoroughly explore the strengths and weaknesses of our approach by evaluating the effect on translation quality for nine major languages. In addition, we show that it is possible to attain a significant improvement in translation quality for even non-structured machine translation by reranking filtered parses of k-best string output.","PeriodicalId":16243,"journal":{"name":"Journal of Information Processing","volume":"23 1","pages":"299-321"},"PeriodicalIF":0.0000,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"A Generalized Dependency Tree Language Model for SMT\",\"authors\":\"John Richardson, Taku Kudo, H. Kazawa, S. Kurohashi\",\"doi\":\"10.5715/JNLP.23.299\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we describe a generalized dependency tree language model for machine translation. We consider in detail the question of how to define tree-based n-grams, or ‘t-treelets’, and thoroughly explore the strengths and weaknesses of our approach by evaluating the effect on translation quality for nine major languages. In addition, we show that it is possible to attain a significant improvement in translation quality for even non-structured machine translation by reranking filtered parses of k-best string output.\",\"PeriodicalId\":16243,\"journal\":{\"name\":\"Journal of Information Processing\",\"volume\":\"23 1\",\"pages\":\"299-321\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Information Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5715/JNLP.23.299\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Information Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5715/JNLP.23.299","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 3

摘要

本文描述了一种用于机器翻译的广义依赖树语言模型。我们详细考虑了如何定义基于树的n-图或“t-树”的问题，并通过评估对九种主要语言的翻译质量的影响，彻底探讨了我们方法的优缺点。此外，我们表明，通过对k-最佳字符串输出的过滤解析进行重新排序，即使是非结构化机器翻译，也可以显著提高翻译质量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Generalized Dependency Tree Language Model for SMT

In this paper we describe a generalized dependency tree language model for machine translation. We consider in detail the question of how to define tree-based n-grams, or ‘t-treelets’, and thoroughly explore the strengths and weaknesses of our approach by evaluating the effect on translation quality for nine major languages. In addition, we show that it is possible to attain a significant improvement in translation quality for even non-structured machine translation by reranking filtered parses of k-best string output.

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

Journal of Information Processing Computer Science-Computer Science (all)

CiteScore

1.20

自引率

0.00%

发文量