The goal of this paper is to show how to accomplish a more enjoyable and enthusiastic dialogue through the analysis of human-to-human conversational dialogues. We first created a conversational dialogue corpus annotated with two types of tags: one type indicates the particular aspects of the utterance itself, while the other indicates the degree of enthusiasm. We then investigated the relationship between these tags. Our results indicate that affective and cooperative utterances are significant to enthusiastic dialogue.
{"title":"Relationship between Utterances and “Enthusiasm” in Non-task-oriented Conversational Dialogue","authors":"Ryoko Tokuhisa, R. Terashima","doi":"10.3115/1654595.1654628","DOIUrl":"https://doi.org/10.3115/1654595.1654628","url":null,"abstract":"The goal of this paper is to show how to accomplish a more enjoyable and enthusiastic dialogue through the analysis of human-to-human conversational dialogues. We first created a conversational dialogue corpus annotated with two types of tags: one type indicates the particular aspects of the utterance itself, while the other indicates the degree of enthusiasm. We then investigated the relationship between these tags. Our results indicate that affective and cooperative utterances are significant to enthusiastic dialogue.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132684513","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 investigates semantic and pragmatic presupposition in Discourse Representation Theory (DRT) and enhances the pragmatic perspective of presupposition in DRT. In doing so, it draws attention to the need to account for agent presupposition (i.e. both speaker and hearer presupposition) when dealing with pragmatic presupposition. Furthermore, this paper links this pragmatic conception of presupposition with the semantic one (sentence presupposition) through using 'information checks' which agents are hypothesized to employ when making and receiving utterances.
{"title":"Semantic and Pragmatic Presupposition in Discourse Representation Theory","authors":"Yafa Al-Raheb","doi":"10.3115/1654595.1654610","DOIUrl":"https://doi.org/10.3115/1654595.1654610","url":null,"abstract":"This paper investigates semantic and pragmatic presupposition in Discourse Representation Theory (DRT) and enhances the pragmatic perspective of presupposition in DRT. In doing so, it draws attention to the need to account for agent presupposition (i.e. both speaker and hearer presupposition) when dealing with pragmatic presupposition. Furthermore, this paper links this pragmatic conception of presupposition with the semantic one (sentence presupposition) through using 'information checks' which agents are hypothesized to employ when making and receiving utterances.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121088873","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}
R. Vieira, Eckhard Bick, J. Coelho, Vinicius M. Muller, Sandra Collovini, José G. C. de Souza, L. H. M. Rino
This paper presents an evaluation of indirect anaphor resolution which considers as lexical resource the semantic tagging provided by the PALAVRAS parser. We describe the semantic tagging process and a corpus experiment.
{"title":"Semantic tagging for resolution of indirect anaphora","authors":"R. Vieira, Eckhard Bick, J. Coelho, Vinicius M. Muller, Sandra Collovini, José G. C. de Souza, L. H. M. Rino","doi":"10.3115/1654595.1654611","DOIUrl":"https://doi.org/10.3115/1654595.1654611","url":null,"abstract":"This paper presents an evaluation of indirect anaphor resolution which considers as lexical resource the semantic tagging provided by the PALAVRAS parser. We describe the semantic tagging process and a corpus experiment.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121300021","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 study the interplay of the discourse structure of a scientific argument with formal citations. One subproblem of this is to classify academic citations in scientific articles according to their rhetorical function, e.g., as a rival approach, as a part of the solution, or as a flawed approach that justifies the current research. Here, we introduce our annotation scheme with 12 categories, and present an agreement study.
{"title":"An annotation scheme for citation function","authors":"Simone Teufel, Advaith Siddharthan, Dan Tidhar","doi":"10.3115/1654595.1654612","DOIUrl":"https://doi.org/10.3115/1654595.1654612","url":null,"abstract":"We study the interplay of the discourse structure of a scientific argument with formal citations. One subproblem of this is to classify academic citations in scientific articles according to their rhetorical function, e.g., as a rival approach, as a part of the solution, or as a flawed approach that justifies the current research. Here, we introduce our annotation scheme with 12 categories, and present an agreement study.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131452885","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}
A key problem for models of dialogue is to explain how semantic co-ordination in dialogue is achieved and sustained. This paper presents findings from a series of Maze Task experiments which are not readily explained by the primary co-ordination mechanisms of existing models. It demonstrates that alignment in dialogue is not simply an outcome of successful interaction, but a communicative resource exploited by interlocutors in converging on a semantic model. We argue this suggests mechanisms of co-ordination in dialogue which are of relevance for a general account of how semantic co-ordination is achieved.
{"title":"Semantic negotiation in dialogue: the mechanisms of alignment","authors":"Gregory J. Mills, P. Healey","doi":"10.3115/1622064.1622072","DOIUrl":"https://doi.org/10.3115/1622064.1622072","url":null,"abstract":"A key problem for models of dialogue is to explain how semantic co-ordination in dialogue is achieved and sustained. This paper presents findings from a series of Maze Task experiments which are not readily explained by the primary co-ordination mechanisms of existing models. It demonstrates that alignment in dialogue is not simply an outcome of successful interaction, but a communicative resource exploited by interlocutors in converging on a semantic model. We argue this suggests mechanisms of co-ordination in dialogue which are of relevance for a general account of how semantic co-ordination is achieved.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"597 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":"116557307","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}
R. Fernández, Matthew Frampton, Patrick Ehlen, Matthew Purver, S. Peters
We describe a process for automatically detecting decision-making sub-dialogues in transcripts of multi-party, human-human meetings. Extending our previous work on action item identification, we propose a structured approach that takes into account the different roles utterances play in the decision-making process. We show that this structured approach outperforms the accuracy achieved by existing decision detection systems based on flat annotations, while enabling the extraction of more fine-grained information that can be used for summarization and reporting.
{"title":"Modelling and Detecting Decisions in Multi-party Dialogue","authors":"R. Fernández, Matthew Frampton, Patrick Ehlen, Matthew Purver, S. Peters","doi":"10.3115/1622064.1622095","DOIUrl":"https://doi.org/10.3115/1622064.1622095","url":null,"abstract":"We describe a process for automatically detecting decision-making sub-dialogues in transcripts of multi-party, human-human meetings. Extending our previous work on action item identification, we propose a structured approach that takes into account the different roles utterances play in the decision-making process. We show that this structured approach outperforms the accuracy achieved by existing decision detection systems based on flat annotations, while enabling the extraction of more fine-grained information that can be used for summarization and reporting.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"377 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":"121761878","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 present a development pipeline and associated algorithms designed to make grammarbased generation easier to deploy in implemented dialogue systems. Our approach realizes a practical trade-off between the capabilities of a system's generation component and the authoring and maintenance burdens imposed on the generation content author for a deployed system. To evaluate our approach, we performed a human rating study with system builders who work on a common largescale spoken dialogue system. Our results demonstrate the viability of our approach and illustrate authoring/performance trade-offs between hand-authored text, our grammar-based approach, and a competing shallow statistical NLG technique.
{"title":"Making Grammar-Based Generation Easier to Deploy in Dialogue Systems","authors":"D. DeVault, D. Traum, Ron Artstein","doi":"10.3115/1622064.1622102","DOIUrl":"https://doi.org/10.3115/1622064.1622102","url":null,"abstract":"We present a development pipeline and associated algorithms designed to make grammarbased generation easier to deploy in implemented dialogue systems. Our approach realizes a practical trade-off between the capabilities of a system's generation component and the authoring and maintenance burdens imposed on the generation content author for a deployed system. To evaluate our approach, we performed a human rating study with system builders who work on a common largescale spoken dialogue system. Our results demonstrate the viability of our approach and illustrate authoring/performance trade-offs between hand-authored text, our grammar-based approach, and a competing shallow statistical NLG technique.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"25 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":"130469649","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 presents a coding protocol that allows naive users to annotate dialogue transcripts for anaphora and ellipsis. Cohen's kappa statistic demonstrates that the protocol is sufficiently robust in terms of reliability. It is proposed that quantitative ellipsis data may be used as an index of mutual-engagement. Current and potential uses of ellipsis coding are described.
{"title":"Quantifying Ellipsis in Dialogue: an index of mutual understanding","authors":"Marcus Colman, Arash Eshghi, P. Healey","doi":"10.3115/1622064.1622083","DOIUrl":"https://doi.org/10.3115/1622064.1622083","url":null,"abstract":"This paper presents a coding protocol that allows naive users to annotate dialogue transcripts for anaphora and ellipsis. Cohen's kappa statistic demonstrates that the protocol is sufficiently robust in terms of reliability. It is proposed that quantitative ellipsis data may be used as an index of mutual-engagement. Current and potential uses of ellipsis coding are described.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"94 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":"126860469","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 propose to use user simulation for testing during the development of a sophisticated dialog system. While the limited behaviors of the state-of-the-art user simulation may not cover important aspects in the dialog system testing, our proposed approach extends the functionality of the simulation so that it can be used at least for the early stage testing before the system reaches stable performance for evaluation involving human users. The proposed approach includes a set of evaluation measures that can be computed automatically from the interaction logs between the user simulator and the dialog system. We first validate these measures on human user dialogs using user satisfaction scores. We also build a regression model to estimate the user satisfaction scores using these evaluation measures. Then, we apply the evaluation measures on a simulated dialog corpus trained from the real user corpus. We show that the user satisfaction scores estimated from the simulated corpus are not statistically different from the real users' satisfaction scores.
{"title":"User Simulation as Testing for Spoken Dialog Systems","authors":"H. Ai, F. Weng","doi":"10.3115/1622064.1622097","DOIUrl":"https://doi.org/10.3115/1622064.1622097","url":null,"abstract":"We propose to use user simulation for testing during the development of a sophisticated dialog system. While the limited behaviors of the state-of-the-art user simulation may not cover important aspects in the dialog system testing, our proposed approach extends the functionality of the simulation so that it can be used at least for the early stage testing before the system reaches stable performance for evaluation involving human users. The proposed approach includes a set of evaluation measures that can be computed automatically from the interaction logs between the user simulator and the dialog system. We first validate these measures on human user dialogs using user satisfaction scores. We also build a regression model to estimate the user satisfaction scores using these evaluation measures. Then, we apply the evaluation measures on a simulated dialog corpus trained from the real user corpus. We show that the user satisfaction scores estimated from the simulated corpus are not statistically different from the real users' satisfaction scores.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"87 5 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":"123175003","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 look at the average frequency of contrastive connectives in the SPaRKy Restaurant Corpus with respect to realization ratings by human judges. We implement a discriminative n-gram ranker to model these ratings and analyze the resulting n-gram weights to determine if our ranker learns this distribution. Surprisingly, our ranker learns to avoid contrastive connectives. We look at possible explanations for this distribution, and recommend improvements to both the generator and ranker of the sentence plans/realizations.
{"title":"Learning Contrastive Connectives in Sentence Realization Ranking","authors":"C. Nakatsu","doi":"10.3115/1622064.1622078","DOIUrl":"https://doi.org/10.3115/1622064.1622078","url":null,"abstract":"We look at the average frequency of contrastive connectives in the SPaRKy Restaurant Corpus with respect to realization ratings by human judges. We implement a discriminative n-gram ranker to model these ratings and analyze the resulting n-gram weights to determine if our ranker learns this distribution. Surprisingly, our ranker learns to avoid contrastive connectives. We look at possible explanations for this distribution, and recommend improvements to both the generator and ranker of the sentence plans/realizations.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"86 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":"124949768","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：