{"title":"中欧洲语言的消歧线性词翻译","authors":"Márton Makrai","doi":"10.1109/COGINFOCOM.2015.7390618","DOIUrl":null,"url":null,"abstract":"An earlier paper used triangulated word translations as seed in linear translation between medium European languages. The present work improves upon it by handling word ambiguity both in the main (i.e. source and target) languages and in the pivot by training a multi-prototype vector space model in the former, filtering triangles based on scores computed by a linear model trained with direct (non-triangulated) translations, and finally translating the whole vocabulary with a linear translation trained on filtered triangles (in addition to direct ones).","PeriodicalId":377891,"journal":{"name":"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Disambiguated linear word translation in medium European languages\",\"authors\":\"Márton Makrai\",\"doi\":\"10.1109/COGINFOCOM.2015.7390618\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An earlier paper used triangulated word translations as seed in linear translation between medium European languages. The present work improves upon it by handling word ambiguity both in the main (i.e. source and target) languages and in the pivot by training a multi-prototype vector space model in the former, filtering triangles based on scores computed by a linear model trained with direct (non-triangulated) translations, and finally translating the whole vocabulary with a linear translation trained on filtered triangles (in addition to direct ones).\",\"PeriodicalId\":377891,\"journal\":{\"name\":\"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/COGINFOCOM.2015.7390618\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COGINFOCOM.2015.7390618","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Disambiguated linear word translation in medium European languages
An earlier paper used triangulated word translations as seed in linear translation between medium European languages. The present work improves upon it by handling word ambiguity both in the main (i.e. source and target) languages and in the pivot by training a multi-prototype vector space model in the former, filtering triangles based on scores computed by a linear model trained with direct (non-triangulated) translations, and finally translating the whole vocabulary with a linear translation trained on filtered triangles (in addition to direct ones).