{"title":"多轮槽标注的扬声器敏感双记忆网络","authors":"Young-Bum Kim, Sungjin Lee, R. Sarikaya","doi":"10.1109/ASRU.2017.8268983","DOIUrl":null,"url":null,"abstract":"In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks which encode utterances differently depending on the speaker. This addresses the different extents of information available to the system — the system knows only the surface form of user utterances while it has the exact semantics of system output. We performed experiments on real user data from Microsoft Cortana, a commercial personal assistant. The result showed a significant performance improvement over the state-of-the-art slot tagging models using contextual information.","PeriodicalId":290868,"journal":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Speaker-sensitive dual memory networks for multi-turn slot tagging\",\"authors\":\"Young-Bum Kim, Sungjin Lee, R. Sarikaya\",\"doi\":\"10.1109/ASRU.2017.8268983\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks which encode utterances differently depending on the speaker. This addresses the different extents of information available to the system — the system knows only the surface form of user utterances while it has the exact semantics of system output. We performed experiments on real user data from Microsoft Cortana, a commercial personal assistant. The result showed a significant performance improvement over the state-of-the-art slot tagging models using contextual information.\",\"PeriodicalId\":290868,\"journal\":{\"name\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ASRU.2017.8268983\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2017.8268983","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Speaker-sensitive dual memory networks for multi-turn slot tagging
In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks which encode utterances differently depending on the speaker. This addresses the different extents of information available to the system — the system knows only the surface form of user utterances while it has the exact semantics of system output. We performed experiments on real user data from Microsoft Cortana, a commercial personal assistant. The result showed a significant performance improvement over the state-of-the-art slot tagging models using contextual information.