ACM Trans. Speech Lang. Process.最新文献_第7页

Promoting extension and reuse in a spoken dialog manager: An evaluation of the queen's communicator 在口语对话管理器中促进扩展和重用:对女王通信器的评价

ACM Trans. Speech Lang. Process. Pub Date : 2007-07-01 DOI: 10.1145/1255171.1255173

Philip Hanna, Ian M. O'Neill, C. Wootton, M. McTear

引用次数: 10

Chinese semantic dependency analysis: Construction of a treebank and its use in classification 汉语语义依赖分析:树库的构建及其在分类中的应用

ACM Trans. Speech Lang. Process. Pub Date : 2007-05-01 DOI: 10.1145/1233912.1233914

Jiajun Yan, D. Bracewell, S. Kuroiwa, F. Ren

引用次数: 3

The Pyramid Method: Incorporating human content selection variation in summarization evaluation 金字塔法:在总结评价中结合人的内容选择变化

ACM Trans. Speech Lang. Process. Pub Date : 2007-05-01 DOI: 10.1145/1233912.1233913

A. Nenkova, R. Passonneau, Kathleen McKeown

引用次数: 339

Confidence estimation for NLP applications NLP应用的置信度估计

ACM Trans. Speech Lang. Process. Pub Date : 2006-10-01 DOI: 10.1145/1177055.1177057

Simona Gandrabur, George F. Foster, G. Lapalme

引用次数: 45

An active approach to spoken language processing 口语处理的积极方法

ACM Trans. Speech Lang. Process. Pub Date : 2006-10-01 DOI: 10.1145/1177055.1177056

Dilek Z. Hakkani-Tür, G. Riccardi, Gökhan Tür

{"title":"An active approach to spoken language processing","authors":"Dilek Z. Hakkani-Tür, G. Riccardi, Gökhan Tür","doi":"10.1145/1177055.1177056","DOIUrl":"https://doi.org/10.1145/1177055.1177056","url":null,"abstract":"State of the art data-driven speech and language processing systems require a large amount of human intervention ranging from data annotation to system prototyping. In the traditional supervised passive approach, the system is trained on a given number of annotated data samples and evaluated using a separate test set. Then more data is collected arbitrarily, annotated, and the whole cycle is repeated. In this article, we propose the active approach where the system itself selects its own training data, evaluates itself and re-trains when necessary. We first employ active learning which aims to automatically select the examples that are likely to be the most informative for a given task. We use active learning for both selecting the examples to label and the examples to re-label in order to correct labeling errors. Furthermore, the system automatically evaluates itself using active evaluation to keep track of the unexpected events and decides on-demand to label more examples. The active approach enables dynamic adaptation of spoken language processing systems to unseen or unexpected events for nonstationary input while reducing the manual annotation effort significantly. We have evaluated the active approach with the AT&T spoken dialog system used for customer care applications. In this article, we present our results for both automatic speech recognition and spoken language understanding.","PeriodicalId":412532,"journal":{"name":"ACM Trans. Speech Lang. Process.","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127127966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 31

One story, one flow: Hidden Markov Story Models for multilingual multidocument summarization 一个故事，一个流程:多语言多文档摘要的隐马尔可夫故事模型

ACM Trans. Speech Lang. Process. Pub Date : 2006-07-01 DOI: 10.1145/1149290.1151099

Pascale Fung, G. Ngai

{"title":"One story, one flow: Hidden Markov Story Models for multilingual multidocument summarization","authors":"Pascale Fung, G. Ngai","doi":"10.1145/1149290.1151099","DOIUrl":"https://doi.org/10.1145/1149290.1151099","url":null,"abstract":"This article presents a multidocument, multilingual, theme-based summarization system based on modeling text cohesion (story flow). Conventional extractive summarization systems which pick out salient sentences to include in a summary often disregard any flow or sequence that might exist between these sentences. We argue that such inherent text cohesion exists and is (1) specific to a particular story and (2) specific to a particular language. Documents within the same story, and in the same language, share a common story flow, and this flow differs across stories, and across languages. We propose using Hidden Markov Models (HMMs) as story models. An unsupervised segmental K-means method is used to iteratively cluster multiple documents into different topics (stories) and learn the parameters of parallel Hidden Markov Story Models (HMSM), one for each story. We compare story models within and across stories and within and across languages (English and Chinese). The experimental results support our “one story, one flow” and “one language, one flow” hypotheses. We also propose a Naïve Bayes classifier for document summarization. The performance of our summarizer is superior to conventional methods that do not incorporate text cohesion information. Our HMSM method also provides a simple way to compile a single metasummary for multiple documents from individual summaries via state labeled sentences.","PeriodicalId":412532,"journal":{"name":"ACM Trans. Speech Lang. Process.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121220976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 63

High-quality speech-to-speech translation for computer-aided language learning 用于计算机辅助语言学习的高质量语音到语音翻译

ACM Trans. Speech Lang. Process. Pub Date : 2006-07-01 DOI: 10.1145/1149290.1149291

Chao Wang, S. Seneff

引用次数: 12

Broad coverage paragraph segmentation across languages and domains 广泛覆盖跨语言和领域的段落分割

ACM Trans. Speech Lang. Process. Pub Date : 2006-07-01 DOI: 10.1145/1149290.1151098

C. Sporleder, Mirella Lapata

引用次数: 21

Acoustic environment classification 声环境分类

ACM Trans. Speech Lang. Process. Pub Date : 2006-07-01 DOI: 10.1145/1149290.1149292

Ling Ma, B. Milner, Dan J. Smith

引用次数: 149

Automatic expansion of domain-specific lexicons by term categorization 通过术语分类自动扩展特定于领域的词汇

ACM Trans. Speech Lang. Process. Pub Date : 2006-05-01 DOI: 10.1145/1138379.1138380

Henri Avancini, A. Lavelli, F. Sebastiani, Roberto Zanoli

{"title":"Automatic expansion of domain-specific lexicons by term categorization","authors":"Henri Avancini, A. Lavelli, F. Sebastiani, Roberto Zanoli","doi":"10.1145/1138379.1138380","DOIUrl":"https://doi.org/10.1145/1138379.1138380","url":null,"abstract":"We discuss an approach to the automatic expansion ofdomain-specific lexicons, that is, to the problem ofextending, for each ci in a predefined setC ={c1,…,cm} ofsemantic domains, an initial lexiconLi0 into a larger lexiconLi1. Our approach relies onterm categorization, defined as the task of labelingpreviously unlabeled terms according to a predefined set ofdomains. We approach this as a supervised learning problem in whichterm classifiers are built using the initial lexicons as trainingdata. Dually to classic text categorization tasks in whichdocuments are represented as vectors in a space of terms, werepresent terms as vectors in a space of documents. We present theresults of a number of experiments in which we use a boosting-basedlearning device for training our term classifiers. We test theeffectiveness of our method by using WordNetDomains, a well-knownlarge set of domain-specific lexicons, as a benchmark. Ourexperiments are performed using the documents in the Reuters CorpusVolume 1 as implicit representations for our terms.","PeriodicalId":412532,"journal":{"name":"ACM Trans. Speech Lang. Process.","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129315441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 20