In this paper DiaGen is presented, a tool that provides support in generating code for embedded dialogue applications. By aid of it, the dialogue development process is speeded up considerably. At the same time it is guaranteed that only well-formed and well-defined constructs are used. Having had its roots in the EU-funded project GEMINI, fundamental changes were necessary to adopt it to the requirements of the application environment. Additionally within this paper the basics of embedded speech dialogue systems are covered.
{"title":"From GEMINI to DiaGen: Improving Development of Speech Dialogues for Embedded Systems","authors":"Stefan W. Hamerich","doi":"10.3115/1622064.1622082","DOIUrl":"https://doi.org/10.3115/1622064.1622082","url":null,"abstract":"In this paper DiaGen is presented, a tool that provides support in generating code for embedded dialogue applications. By aid of it, the dialogue development process is speeded up considerably. At the same time it is guaranteed that only well-formed and well-defined constructs are used. Having had its roots in the EU-funded project GEMINI, fundamental changes were necessary to adopt it to the requirements of the application environment. Additionally within this paper the basics of embedded speech dialogue systems are covered.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125422695","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}
The invention relates to members of the MAGE-Xp family of nucleic acid molecules. These molecules differ from the previously described MAGE nucleic acid molecules in that members of the MAGE-Xp family do not hybridize to the previously identified MAGE sequences. Further, the members of the MAGE-Xp family are found on the Xp arm of the X chromosome rather than on the Xq chromosome, as was the case with the previously identified MAGE genes.
{"title":"A Simple Method for Resolution of Definite Reference in a Shared Visual Context","authors":"A. Siebert, David Schlangen","doi":"10.3115/1622064.1622080","DOIUrl":"https://doi.org/10.3115/1622064.1622080","url":null,"abstract":"The invention relates to members of the MAGE-Xp family of nucleic acid molecules. These molecules differ from the previously described MAGE nucleic acid molecules in that members of the MAGE-Xp family do not hybridize to the previously identified MAGE sequences. Further, the members of the MAGE-Xp family are found on the Xp arm of the X chromosome rather than on the Xq chromosome, as was the case with the previously identified MAGE genes.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129984166","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}
Y. Katagiri, Y. Matsusaka, Yasuharu Den, M. Enomoto, M. Ishizaki, K. Takanashi
An attempt was made to statistically estimate proposals which survived the discussion to be incorporated in the final agreement in an instance of a Japanese design conversation. Low level speech and vision features of hearer behaviors corresponding to aiduti, noddings and gaze were found to be a positive predictor of survival. The result suggests that non-linguistic hearer responses work as implicit proposal filters in consensus building, and could provide promising candidate features for the purpose of recognition and summarization of meeting events.
{"title":"Implicit Proposal Filtering in Multi-Party Consensus-Building Conversations","authors":"Y. Katagiri, Y. Matsusaka, Yasuharu Den, M. Enomoto, M. Ishizaki, K. Takanashi","doi":"10.3115/1622064.1622084","DOIUrl":"https://doi.org/10.3115/1622064.1622084","url":null,"abstract":"An attempt was made to statistically estimate proposals which survived the discussion to be incorporated in the final agreement in an instance of a Japanese design conversation. Low level speech and vision features of hearer behaviors corresponding to aiduti, noddings and gaze were found to be a positive predictor of survival. The result suggests that non-linguistic hearer responses work as implicit proposal filters in consensus building, and could provide promising candidate features for the purpose of recognition and summarization of meeting events.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127469719","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}
When people engage in conversation, they adapt the way they speak to the speaking style of their conversational partner in a variety of ways. For example, they may adopt a certain way of describing something based upon the way their conversational partner describes it, or adapt their pitch range or speaking rate to a conversational partner's. They may even align their turn-taking style or use of cue phrases to match their partner's. These types of entrainment have been shown to correlate with various measures of task success and dialogue naturalness. While there is considerable evidence for lexical entrainment from laboratory experiments, much less is known about other types of acoustic-prosodic and discourse-level entrainment and little work has been done to examine entrainments in multiple modalities for the same dialogue. We will discuss work on entrainment in multiple dimensions in the Columbia Games Corpus. Our goal is to understand how the different varieties of entrainment correlate with one another and to determine which types of entrainment will be both useful and feasible for Spoken Dialogue Systems.
{"title":"Speaking More Like You: Lexical, Acoustic/Prosodic, and Discourse Entrainment in Spoken Dialogue Systems","authors":"Julia Hirschberg","doi":"10.3115/1622064.1622090","DOIUrl":"https://doi.org/10.3115/1622064.1622090","url":null,"abstract":"When people engage in conversation, they adapt the way they speak to the speaking style of their conversational partner in a variety of ways. For example, they may adopt a certain way of describing something based upon the way their conversational partner describes it, or adapt their pitch range or speaking rate to a conversational partner's. They may even align their turn-taking style or use of cue phrases to match their partner's. These types of entrainment have been shown to correlate with various measures of task success and dialogue naturalness. While there is considerable evidence for lexical entrainment from laboratory experiments, much less is known about other types of acoustic-prosodic and discourse-level entrainment and little work has been done to examine entrainments in multiple modalities for the same dialogue. We will discuss work on entrainment in multiple dimensions in the Columbia Games Corpus. Our goal is to understand how the different varieties of entrainment correlate with one another and to determine which types of entrainment will be both useful and feasible for Spoken Dialogue Systems.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115292524","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}
Mikio Nakano, Kotaro Funakoshi, Yuji Hasegawa, H. Tsujino
This paper presents a novel framework for building symbol-level control modules of animated agents and robots having a spoken dialogue interface. It features distributed modules called experts each of which is specialized to perform certain kinds of tasks. A common interface that all experts must support is specified, and any kind of expert can be incorporated if it has the interface. Several modules running in parallel coordinate the experts by accessing them through the interface, so that the whole system can achieve flexible control, such as interruption handling and parallel task execution.
{"title":"A Framework for Building Conversational Agents Based on a Multi-Expert Model","authors":"Mikio Nakano, Kotaro Funakoshi, Yuji Hasegawa, H. Tsujino","doi":"10.3115/1622064.1622081","DOIUrl":"https://doi.org/10.3115/1622064.1622081","url":null,"abstract":"This paper presents a novel framework for building symbol-level control modules of animated agents and robots having a spoken dialogue interface. It features distributed modules called experts each of which is specialized to perform certain kinds of tasks. A common interface that all experts must support is specified, and any kind of expert can be incorporated if it has the interface. Several modules running in parallel coordinate the experts by accessing them through the interface, so that the whole system can achieve flexible control, such as interruption handling and parallel task execution.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115491518","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 introduce the Degrees of Grounding model, which defines the extent to which material being discussed in a dialogue has been grounded. This model has been developed and evaluated by a corpus analysis, and includes a set of types of evidence of understanding, a set of degrees of groundedness, a set of grounding criteria, and methods for identifying each of these. We describe how this model can be used for dialogue management.
{"title":"Degrees of Grounding Based on Evidence of Understanding","authors":"Antonio Roque, D. Traum","doi":"10.3115/1622064.1622073","DOIUrl":"https://doi.org/10.3115/1622064.1622073","url":null,"abstract":"We introduce the Degrees of Grounding model, which defines the extent to which material being discussed in a dialogue has been grounded. This model has been developed and evaluated by a corpus analysis, and includes a set of types of evidence of understanding, a set of degrees of groundedness, a set of grounding criteria, and methods for identifying each of these. We describe how this model can be used for dialogue management.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131133498","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}
Argumentation is an emerging topic in the field of human computer dialogue. In this paper we describe a novel approach to dialogue management that has been developed to achieve persuasion using a textual argumentation dialogue system. The paper introduces a layered management architecture that mixes task-oriented dialogue techniques with chatbot techniques to achieve better persuasiveness in the dialogue.
{"title":"Argumentative Human Computer Dialogue for Automated Persuasion","authors":"Pierre Yves Andrews, S. Manandhar, M. Boni","doi":"10.3115/1622064.1622093","DOIUrl":"https://doi.org/10.3115/1622064.1622093","url":null,"abstract":"Argumentation is an emerging topic in the field of human computer dialogue. In this paper we describe a novel approach to dialogue management that has been developed to achieve persuasion using a textual argumentation dialogue system. The paper introduces a layered management architecture that mixes task-oriented dialogue techniques with chatbot techniques to achieve better persuasiveness in the dialogue.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131312965","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}
Milica Gasic, Simon Keizer, François Mairesse, J. Schatzmann, Blaise Thomson, Kai Yu, S. Young
This paper investigates the claim that a dialogue manager modelled as a Partially Observable Markov Decision Process (POMDP) can achieve improved robustness to noise compared to conventional state-based dialogue managers. Using the Hidden Information State (HIS) POMDP dialogue manager as an exemplar, and an MDP-based dialogue manager as a baseline, evaluation results are presented for both simulated and real dialogues in a Tourist Information Domain. The results on the simulated data show that the inherent ability to model uncertainty, allows the POMDP model to exploit alternative hypotheses from the speech understanding system. The results obtained from a user trial show that the HIS system with a trained policy performed significantly better than the MDP baseline.
{"title":"Training and Evaluation of the HIS POMDP Dialogue System in Noise","authors":"Milica Gasic, Simon Keizer, François Mairesse, J. Schatzmann, Blaise Thomson, Kai Yu, S. Young","doi":"10.3115/1622064.1622087","DOIUrl":"https://doi.org/10.3115/1622064.1622087","url":null,"abstract":"This paper investigates the claim that a dialogue manager modelled as a Partially Observable Markov Decision Process (POMDP) can achieve improved robustness to noise compared to conventional state-based dialogue managers. Using the Hidden Information State (HIS) POMDP dialogue manager as an exemplar, and an MDP-based dialogue manager as a baseline, evaluation results are presented for both simulated and real dialogues in a Tourist Information Domain. The results on the simulated data show that the inherent ability to model uncertainty, allows the POMDP model to exploit alternative hypotheses from the speech understanding system. The results obtained from a user trial show that the HIS system with a trained policy performed significantly better than the MDP baseline.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131397447","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}
Humans produce speech incrementally and on-line as the dialogue progresses using information from several different sources in parallel. A dialogue system that generates output in a stepwise manner and not in preplanned syntactically correct sentences needs to signal how new dialogue contributions relate to previous discourse. This paper describes a data collection which is the foundation for an effort towards more human-like language generation in DEAL, a spoken dialogue system developed at KTH. Two annotators labelled cue phrases in the corpus with high inter-annotator agreement (kappa coefficient 0.82).
{"title":"Speaking without knowing what to say... or when to end","authors":"Anna Hjalmarsson","doi":"10.3115/1622064.1622077","DOIUrl":"https://doi.org/10.3115/1622064.1622077","url":null,"abstract":"Humans produce speech incrementally and on-line as the dialogue progresses using information from several different sources in parallel. A dialogue system that generates output in a stepwise manner and not in preplanned syntactically correct sentences needs to signal how new dialogue contributions relate to previous discourse. This paper describes a data collection which is the foundation for an effort towards more human-like language generation in DEAL, a spoken dialogue system developed at KTH. Two annotators labelled cue phrases in the corpus with high inter-annotator agreement (kappa coefficient 0.82).","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121869711","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}
Voice-Rate is an experimental dialog system through which a user can call to get product information. In this paper, we describe an optimal dialog management algorithm for Voice-Rate. Our algorithm uses a POMDP framework, which is probabilistic and captures uncertainty in speech recognition and user knowledge. We propose a novel method to learn a user knowledge model from a review database. Simulation results show that the POMDP system performs significantly better than a deterministic baseline system in terms of both dialog failure rate and dialog interaction time. To the best of our knowledge, our work is the first to show that a POMDP can be successfully used for disambiguation in a complex voice search domain like Voice-Rate.
{"title":"Optimal Dialog in Consumer-Rating Systems using POMDP Framework","authors":"Zhifei Li, Patrick Nguyen, G. Zweig","doi":"10.3115/1622064.1622086","DOIUrl":"https://doi.org/10.3115/1622064.1622086","url":null,"abstract":"Voice-Rate is an experimental dialog system through which a user can call to get product information. In this paper, we describe an optimal dialog management algorithm for Voice-Rate. Our algorithm uses a POMDP framework, which is probabilistic and captures uncertainty in speech recognition and user knowledge. We propose a novel method to learn a user knowledge model from a review database. Simulation results show that the POMDP system performs significantly better than a deterministic baseline system in terms of both dialog failure rate and dialog interaction time. To the best of our knowledge, our work is the first to show that a POMDP can be successfully used for disambiguation in a complex voice search domain like Voice-Rate.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117261062","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：