基于统计机器翻译的神经机器翻译:以波斯语-西班牙语双语低资源场景为例

2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) Pub Date : 2018-12-01 DOI:10.1109/ICMLA.2018.00196

Benyamin Ahmadnia, Parisa Kordjamshidi, Gholamreza Haffari

{"title":"基于统计机器翻译的神经机器翻译:以波斯语-西班牙语双语低资源场景为例","authors":"Benyamin Ahmadnia, Parisa Kordjamshidi, Gholamreza Haffari","doi":"10.1109/ICMLA.2018.00196","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a sequence-to-sequence NMT model on Farsi-Spanish bilingually low-resource language pair. We apply effective preprocessing steps specific for Farsi language and optimize the model for both translation and transliteration. We also propose a loss function that enhances the word alignment and consequently improves translation quality.","PeriodicalId":6533,"journal":{"name":"2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"4 1","pages":"1209-1213"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Neural Machine Translation Advised by Statistical Machine Translation: The Case of Farsi-Spanish Bilingually Low-Resource Scenario\",\"authors\":\"Benyamin Ahmadnia, Parisa Kordjamshidi, Gholamreza Haffari\",\"doi\":\"10.1109/ICMLA.2018.00196\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose a sequence-to-sequence NMT model on Farsi-Spanish bilingually low-resource language pair. We apply effective preprocessing steps specific for Farsi language and optimize the model for both translation and transliteration. We also propose a loss function that enhances the word alignment and consequently improves translation quality.\",\"PeriodicalId\":6533,\"journal\":{\"name\":\"2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)\",\"volume\":\"4 1\",\"pages\":\"1209-1213\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMLA.2018.00196\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMLA.2018.00196","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

摘要

在本文中，我们提出了一种基于波斯语-西班牙语双语低资源语言对的序列到序列NMT模型。我们采用了针对波斯语的有效预处理步骤，并对翻译和音译模型进行了优化。我们还提出了一个损失函数来增强单词对齐从而提高翻译质量。

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

Neural Machine Translation Advised by Statistical Machine Translation: The Case of Farsi-Spanish Bilingually Low-Resource Scenario

In this paper, we propose a sequence-to-sequence NMT model on Farsi-Spanish bilingually low-resource language pair. We apply effective preprocessing steps specific for Farsi language and optimize the model for both translation and transliteration. We also propose a loss function that enhances the word alignment and consequently improves translation quality.

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

2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)

自引率

0.00%

发文量