Marco Dinarelli, Alessandro Moschitti, G. Riccardi
{"title":"口语理解的联合生成和判别模型","authors":"Marco Dinarelli, Alessandro Moschitti, G. Riccardi","doi":"10.1109/SLT.2008.4777840","DOIUrl":null,"url":null,"abstract":"Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a training framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model, depending on string kernels and Support Vector Machines, re-ranks such list. We tested such approach on a new corpus produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"451 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Joint generative and discriminative models for spoken language understanding\",\"authors\":\"Marco Dinarelli, Alessandro Moschitti, G. Riccardi\",\"doi\":\"10.1109/SLT.2008.4777840\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a training framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model, depending on string kernels and Support Vector Machines, re-ranks such list. We tested such approach on a new corpus produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.\",\"PeriodicalId\":186876,\"journal\":{\"name\":\"2008 IEEE Spoken Language Technology Workshop\",\"volume\":\"451 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 IEEE Spoken Language Technology Workshop\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SLT.2008.4777840\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 IEEE Spoken Language Technology Workshop","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SLT.2008.4777840","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Joint generative and discriminative models for spoken language understanding
Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a training framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model, depending on string kernels and Support Vector Machines, re-ranks such list. We tested such approach on a new corpus produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.