葡英统计机器翻译的微调

2009 Seventh Brazilian Symposium in Information and Human Language Technology Pub Date : 2009-09-08 DOI:10.1109/STIL.2009.16

Wilker Aziz, T. Pardo, Ivandré Paraboni

{"title":"葡英统计机器翻译的微调","authors":"Wilker Aziz, T. Pardo, Ivandré Paraboni","doi":"10.1109/STIL.2009.16","DOIUrl":null,"url":null,"abstract":"In previous work we have shown results of a first experiment in Statistical Machine Translation (SMT) for Brazilian Portuguese and American English using state-of-the-art phrase-based models. In this paper we compare a number of training and decoding parameter choices for fine-tuning the system as an attempt to obtain optimal results for this language pair.","PeriodicalId":265848,"journal":{"name":"2009 Seventh Brazilian Symposium in Information and Human Language Technology","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Fine-Tuning in Portuguese-English Statistical Machine Translation\",\"authors\":\"Wilker Aziz, T. Pardo, Ivandré Paraboni\",\"doi\":\"10.1109/STIL.2009.16\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In previous work we have shown results of a first experiment in Statistical Machine Translation (SMT) for Brazilian Portuguese and American English using state-of-the-art phrase-based models. In this paper we compare a number of training and decoding parameter choices for fine-tuning the system as an attempt to obtain optimal results for this language pair.\",\"PeriodicalId\":265848,\"journal\":{\"name\":\"2009 Seventh Brazilian Symposium in Information and Human Language Technology\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-09-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2009 Seventh Brazilian Symposium in Information and Human Language Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/STIL.2009.16\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 Seventh Brazilian Symposium in Information and Human Language Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/STIL.2009.16","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

在之前的工作中，我们展示了使用最先进的基于短语的模型在统计机器翻译(SMT)中对巴西葡萄牙语和美国英语进行的第一次实验的结果。在本文中，我们比较了一些训练和解码参数的选择，以微调系统，试图获得该语言对的最佳结果。

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

Fine-Tuning in Portuguese-English Statistical Machine Translation

In previous work we have shown results of a first experiment in Statistical Machine Translation (SMT) for Brazilian Portuguese and American English using state-of-the-art phrase-based models. In this paper we compare a number of training and decoding parameter choices for fine-tuning the system as an attempt to obtain optimal results for this language pair.

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

2009 Seventh Brazilian Symposium in Information and Human Language Technology

自引率

0.00%

发文量