Why do few working spoken dialogue systems make use of dialogue models in their dialogue management? We find out the causes and propose a generic dialogue model. It promises to bridge the gap between practical dialogue management and (pattern-based) dialogue model through integrating interaction patterns with the underling tasks and modeling interaction patterns via utterance groups using a high level construct different from dialogue act.
{"title":"Bridging the Gap between Dialogue management and dialogue models","authors":"Weiqun Xu, Bo Xu, Taiyi Huang, Hairong Xia","doi":"10.3115/1118121.1118147","DOIUrl":"https://doi.org/10.3115/1118121.1118147","url":null,"abstract":"Why do few working spoken dialogue systems make use of dialogue models in their dialogue management? We find out the causes and propose a generic dialogue model. It promises to bridge the gap between practical dialogue management and (pattern-based) dialogue model through integrating interaction patterns with the underling tasks and modeling interaction patterns via utterance groups using a high level construct different from dialogue act.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812839","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}
Oliver Lemon, A. Gruenstein, Alexis Battle, S. Peters
We explain dialogue management techniques for collaborative activities with humans, involving multiple concurrent tasks. Conversational context for multiple concurrent activities is represented using a "Dialogue Move Tree" and an "Activity Tree" which support multiple interleaved threads of dialogue about different activities and their execution status. We also describe the incremental message selection, aggregation, and generation method employed in the system.
{"title":"Multi-tasking and Collaborative Activities in Dialogue Systems","authors":"Oliver Lemon, A. Gruenstein, Alexis Battle, S. Peters","doi":"10.3115/1118121.1118137","DOIUrl":"https://doi.org/10.3115/1118121.1118137","url":null,"abstract":"We explain dialogue management techniques for collaborative activities with humans, involving multiple concurrent tasks. Conversational context for multiple concurrent activities is represented using a \"Dialogue Move Tree\" and an \"Activity Tree\" which support multiple interleaved threads of dialogue about different activities and their execution status. We also describe the incremental message selection, aggregation, and generation method employed in the system.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123828895","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}
Recent work on natural language processing systems is aimed at more conversational, context-adaptive systems in multiple domains. An important requirement for such a system is the automatic detection of the domain and a domain consistency check of the given speech recognition hypotheses. We report a pilot study addressing these tasks, the underlying data collection and investigate the feasibility of annotating the data reliably by human annotators.
{"title":"Annotating the Semantic Consistency of Speech Recognition Hypotheses","authors":"Iryna Gurevych, R. Porzel, M. Strube","doi":"10.3115/1118121.1118128","DOIUrl":"https://doi.org/10.3115/1118121.1118128","url":null,"abstract":"Recent work on natural language processing systems is aimed at more conversational, context-adaptive systems in multiple domains. An important requirement for such a system is the automatic detection of the domain and a domain consistency check of the given speech recognition hypotheses. We report a pilot study addressing these tasks, the underlying data collection and investigate the feasibility of annotating the data reliably by human annotators.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114561520","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}
While dialogue acts provide a useful schema for characterizing dialogue behaviors in human-computer and human-human dialogues, their utility is limited by the huge effort involved in hand-labelling dialogues with a dialogue act labelling scheme. In this work, we examine whether it is possible to fully automate the tagging task with the goal of enabling rapid creation of corpora for evaluating spoken dialogue systems and comparing them to human-human dialogues. We report results for training and testing an automatic classifier to label the information provider's utterances in spoken human-computer and human-human dialogues with DATE (Dialogue Act Tagging for Evaluation) dialogue act tags. We train and test the DATE tagger on various combinations of the DARPA Communicator June-2000 and October-2001 human-computer corpora, and the CMU human-human corpus in the travel planning domain. Our results show that we can achieve high accuracies on the human-computer data, and surprisingly, that the human-computer data improves accuracy on the human-human data, when only small amounts of human-human training data are available.
尽管对话行为为描述人机对话和人-人对话中的对话行为提供了一种有用的模式，但由于使用对话行为标记方案对对话进行手工标记所涉及的大量工作，它们的效用受到限制。在这项工作中，我们研究了是否有可能完全自动化标记任务，以实现快速创建语料库以评估口语对话系统并将其与人类对话进行比较。我们报告了一个自动分类器的训练和测试结果，该分类器使用DATE (Dialogue Act Tagging for Evaluation)对话行为标签来标记人机口语和人机对话中的信息提供者的话语。我们在DARPA Communicator 2000年6月和2001年10月的人机语料库以及旅行计划领域的CMU人机语料库的各种组合上训练和测试DATE标注器。我们的结果表明，我们可以在人机数据上达到很高的准确性，并且令人惊讶的是，当只有少量的人机训练数据可用时，人机数据提高了人机数据的准确性。
{"title":"Training a Dialogue Act Tagger for Human-human and Human-computer Travel dialogues","authors":"R. Prasad, M. Walker","doi":"10.3115/1118121.1118142","DOIUrl":"https://doi.org/10.3115/1118121.1118142","url":null,"abstract":"While dialogue acts provide a useful schema for characterizing dialogue behaviors in human-computer and human-human dialogues, their utility is limited by the huge effort involved in hand-labelling dialogues with a dialogue act labelling scheme. In this work, we examine whether it is possible to fully automate the tagging task with the goal of enabling rapid creation of corpora for evaluating spoken dialogue systems and comparing them to human-human dialogues. We report results for training and testing an automatic classifier to label the information provider's utterances in spoken human-computer and human-human dialogues with DATE (Dialogue Act Tagging for Evaluation) dialogue act tags. We train and test the DATE tagger on various combinations of the DARPA Communicator June-2000 and October-2001 human-computer corpora, and the CMU human-human corpus in the travel planning domain. Our results show that we can achieve high accuracies on the human-computer data, and surprisingly, that the human-computer data improves accuracy on the human-human data, when only small amounts of human-human training data are available.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121061636","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}
This paper describes a method of processing unknown words in a HPSG-based dialogue system, with acquisition of lexical semantics via clarification questions answered by the user. Use of a highly contextualized semantic representation, together with an utterance-anaphoric view of clarification, allows the clarificational dialogue to be integrated within the grammar and governed by standard rules of conversation.
{"title":"Processing Unknown Words in a Dialogue System","authors":"Matthew Purver","doi":"10.3115/1118121.1118143","DOIUrl":"https://doi.org/10.3115/1118121.1118143","url":null,"abstract":"This paper describes a method of processing unknown words in a HPSG-based dialogue system, with acquisition of lexical semantics via clarification questions answered by the user. Use of a highly contextualized semantic representation, together with an utterance-anaphoric view of clarification, allows the clarificational dialogue to be integrated within the grammar and governed by standard rules of conversation.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"305 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116196121","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}
Dialogue is full of intuitively complete utterances that are not sentential in their outward form, most prototypically the "short answers" used to respond to queries. As is well known, processing such non-sentential utterances (NSUs) is a difficult problem on both theoretical and computational grounds. In this paper we present a corpus-based study of NSUs. We propose a comprehensive, theoretically grounded classification of NSUs in dialogue based on a sub-portion of the British National Corpus (BNC). The study suggests that the interpretation of NSUs is amenable to resolution using a relatively intricate grammar combined with an utterance dynamics approach. That is, a strategy that keeps track of a highly structured dialogue record of entities that get introduced into context as a result of utterances. Complex, domain-based reasoning is not, on the whole, very much in evidence.
{"title":"Non-Sentential Utterances in Dialogue: A: Corpus-Based Study","authors":"R. Fernández, J. Ginzburg","doi":"10.3115/1118121.1118124","DOIUrl":"https://doi.org/10.3115/1118121.1118124","url":null,"abstract":"Dialogue is full of intuitively complete utterances that are not sentential in their outward form, most prototypically the \"short answers\" used to respond to queries. As is well known, processing such non-sentential utterances (NSUs) is a difficult problem on both theoretical and computational grounds. In this paper we present a corpus-based study of NSUs. We propose a comprehensive, theoretically grounded classification of NSUs in dialogue based on a sub-portion of the British National Corpus (BNC). The study suggests that the interpretation of NSUs is amenable to resolution using a relatively intricate grammar combined with an utterance dynamics approach. That is, a strategy that keeps track of a highly structured dialogue record of entities that get introduced into context as a result of utterances. Complex, domain-based reasoning is not, on the whole, very much in evidence.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128613108","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}
In human-computer interaction systems using natural language, the recognition of the topic from user's utterances is an important task. We examine two different perspectives to the problem of topic analysis needed for carrying out a successful dialogue. First, we apply self-organized document maps for modeling the broader subject of discourse based on the occurrence of content words in the dialogue context. On a Finnish corpus of 57 dialogues the method is shown to work well for recognizing subjects of longer dialogue segments, whereas for individual utterances the subject recognition history should perhaps be taken into account. Second, we attempt to identify topically relevant words in the utterances and thus locate the old information ('topic words') and new information ('focus words'). For this we define a probabilistic model and compare different methods for model parameter estimation on a corpus of 189 dialogues. Moreover, the utilization of information regarding the position of the word in the utterance is found to improve the results.
{"title":"Topic Identification in Natural Language Dialogues Using Neural Networks","authors":"K. Lagus, Jukka Kuusisto","doi":"10.3115/1118121.1118135","DOIUrl":"https://doi.org/10.3115/1118121.1118135","url":null,"abstract":"In human-computer interaction systems using natural language, the recognition of the topic from user's utterances is an important task. We examine two different perspectives to the problem of topic analysis needed for carrying out a successful dialogue. First, we apply self-organized document maps for modeling the broader subject of discourse based on the occurrence of content words in the dialogue context. On a Finnish corpus of 57 dialogues the method is shown to work well for recognizing subjects of longer dialogue segments, whereas for individual utterances the subject recognition history should perhaps be taken into account. Second, we attempt to identify topically relevant words in the utterances and thus locate the old information ('topic words') and new information ('focus words'). For this we define a probabilistic model and compare different methods for model parameter estimation on a corpus of 189 dialogues. Moreover, the utilization of information regarding the position of the word in the utterance is found to improve the results.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130093573","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}
This document proposes a new taxonomy for describing the quality of services which are based on spoken dialogue systems (SDSs), and operated via a telephone interface. It is used to classify instrumentally or expert-derived dialogue and system measures, as well as quality features perceived by the user of the service. A comparison is drawn to the quality of human-to-human telephone services, and implications for the development of evaluation frameworks such as PARADISE are discussed.
{"title":"A new Taxonomy for the Quality of Telephone Services Based on Spoken Dialogue Systems","authors":"S. Möller","doi":"10.3115/1118121.1118140","DOIUrl":"https://doi.org/10.3115/1118121.1118140","url":null,"abstract":"This document proposes a new taxonomy for describing the quality of services which are based on spoken dialogue systems (SDSs), and operated via a telephone interface. It is used to classify instrumentally or expert-derived dialogue and system measures, as well as quality features perceived by the user of the service. A comparison is drawn to the quality of human-to-human telephone services, and implications for the development of evaluation frameworks such as PARADISE are discussed.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115828708","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}
Ronnie W. Smith, B. Manning, Jon Rogers, Brian Adams, Mujibur Abdul, Amaury Alvarez
This paper describes a prototype multimodal spoken natural language dialog system for capturing a commander's expectations about planned military actions. Dialog context is used for handling issues concerning military echelons, multiple databases, dynamic name creation, and relative time references.
{"title":"A Dialog Architecture for Military Story Capture","authors":"Ronnie W. Smith, B. Manning, Jon Rogers, Brian Adams, Mujibur Abdul, Amaury Alvarez","doi":"10.3115/1118121.1118144","DOIUrl":"https://doi.org/10.3115/1118121.1118144","url":null,"abstract":"This paper describes a prototype multimodal spoken natural language dialog system for capturing a commander's expectations about planned military actions. Dialog context is used for handling issues concerning military echelons, multiple databases, dynamic name creation, and relative time references.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116728485","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}
We describe a mechanism which receives as input a segmented argument composed of NL sentences, and generates an interpretation. Our mechanism relies on the Minimum Message Length Principle for the selection of an interpretation among candidate options. This enables our mechanism to cope with noisy input in terms of wording, beliefs and argument structure; and reduces its reliance on a particular knowledge representation. The performance of our system was evaluated by distorting automatically generated arguments, and passing them to the system for interpretation. In 75% of the cases, the interpretations produced by the system matched precisely or almost-precisely the representation of the original arguments.
{"title":"A Minimum Message Length Approach for Argument Interpretation","authors":"Ingrid Zukerman, Sarah George","doi":"10.3115/1118121.1118148","DOIUrl":"https://doi.org/10.3115/1118121.1118148","url":null,"abstract":"We describe a mechanism which receives as input a segmented argument composed of NL sentences, and generates an interpretation. Our mechanism relies on the Minimum Message Length Principle for the selection of an interpretation among candidate options. This enables our mechanism to cope with noisy input in terms of wording, beliefs and argument structure; and reduces its reliance on a particular knowledge representation. The performance of our system was evaluated by distorting automatically generated arguments, and passing them to the system for interpretation. In 75% of the cases, the interpretations produced by the system matched precisely or almost-precisely the representation of the original arguments.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133927909","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：