{"title":"基于分层短语的统计机器翻译中抛弃单调组成规则","authors":"Zhongjun He, Yao Meng, Hao Yu","doi":"10.1145/1667780.1667786","DOIUrl":null,"url":null,"abstract":"Hierarchical phrase-based statistical machine translation systems often suffer from a huge rule table. This paper proposed a basic and efficient method for rule table reduction, discarding monotone composed rules. These rules are redundant because they may be monotonically recreated by minimal rules. Experiments show that the rule table is reduced 57%~71% without worsening translation quality.","PeriodicalId":103128,"journal":{"name":"Proceedings of the 3rd International Universal Communication Symposium","volume":"109 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":"{\"title\":\"Discarding monotone composed rule for hierarchical phrase-based statistical machine translation\",\"authors\":\"Zhongjun He, Yao Meng, Hao Yu\",\"doi\":\"10.1145/1667780.1667786\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Hierarchical phrase-based statistical machine translation systems often suffer from a huge rule table. This paper proposed a basic and efficient method for rule table reduction, discarding monotone composed rules. These rules are redundant because they may be monotonically recreated by minimal rules. Experiments show that the rule table is reduced 57%~71% without worsening translation quality.\",\"PeriodicalId\":103128,\"journal\":{\"name\":\"Proceedings of the 3rd International Universal Communication Symposium\",\"volume\":\"109 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-12-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"17\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 3rd International Universal Communication Symposium\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/1667780.1667786\",\"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 3rd International Universal Communication Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1667780.1667786","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Discarding monotone composed rule for hierarchical phrase-based statistical machine translation
Hierarchical phrase-based statistical machine translation systems often suffer from a huge rule table. This paper proposed a basic and efficient method for rule table reduction, discarding monotone composed rules. These rules are redundant because they may be monotonically recreated by minimal rules. Experiments show that the rule table is reduced 57%~71% without worsening translation quality.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
