{"title":"基于领域自适应语言模型的机器翻译","authors":"Lingling Li, Xianlong Chen, Yiling Xu","doi":"10.1109/CIS52066.2020.00033","DOIUrl":null,"url":null,"abstract":"This study presents a domain adaptive language model based on adjustable parameters and domain interpolation. Meanwhile, a method of automatically determining test data domain by language model is proposed. Results show that the perplexity of the proposed language model is significantly lower than that of the baseline of KN smoothing language model on the cross-domain test set. In Chinese-English translation, the BLEU value of machine translation evaluation is also significantly higher than that of baseline model.","PeriodicalId":106959,"journal":{"name":"2020 16th International Conference on Computational Intelligence and Security (CIS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine Translation Based on Domain Adaptive Language Model\",\"authors\":\"Lingling Li, Xianlong Chen, Yiling Xu\",\"doi\":\"10.1109/CIS52066.2020.00033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study presents a domain adaptive language model based on adjustable parameters and domain interpolation. Meanwhile, a method of automatically determining test data domain by language model is proposed. Results show that the perplexity of the proposed language model is significantly lower than that of the baseline of KN smoothing language model on the cross-domain test set. In Chinese-English translation, the BLEU value of machine translation evaluation is also significantly higher than that of baseline model.\",\"PeriodicalId\":106959,\"journal\":{\"name\":\"2020 16th International Conference on Computational Intelligence and Security (CIS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 16th International Conference on Computational Intelligence and Security (CIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIS52066.2020.00033\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 16th International Conference on Computational Intelligence and Security (CIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIS52066.2020.00033","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Machine Translation Based on Domain Adaptive Language Model
This study presents a domain adaptive language model based on adjustable parameters and domain interpolation. Meanwhile, a method of automatically determining test data domain by language model is proposed. Results show that the perplexity of the proposed language model is significantly lower than that of the baseline of KN smoothing language model on the cross-domain test set. In Chinese-English translation, the BLEU value of machine translation evaluation is also significantly higher than that of baseline model.