{"title":"Boon or Bane? Discursive Construction of the Shale Gas Controversy","authors":"Zeynep Cihan Koca-Helvaci","doi":"10.5087/dad.2017.206","DOIUrl":"https://doi.org/10.5087/dad.2017.206","url":null,"abstract":"","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72606198","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}
Attitude or speech reports in English with a non-parenthetical syntax sometimes give rise to interpretations in which the embedded clause, e.g., "John was out of town" in the report " Jill said that John was out of town", seems to convey the main point of the utterance while the attribution predicate, e.g., " Jill said that", merely plays an evidential or source-providing role (Urmson, 1952). Simons (2007) posits that parenthetical readings arise from the interaction between the report and the preceding discourse context, rather than from the syntax or semantics of the reports involved. However, no account of these discourse interactions has been developed in formal semantics. Research on parenthetical reports within frameworks of rhetorical structure has yielded hypotheses about the discourse interactions of parenthetical reports, but these hypotheses are not semantically sound. The goal of this paper is to unify and extend work in semantics and discourse structure to develop a formal, discourse-based account of parenthetical reports that does not suffer the pitfalls faced by current proposals in rhetorical frameworks.
在非括号语法的英语态度或言语报道中，有时会产生这样的解释，即在“Jill said John was out of town”的报道中嵌入的从句，例如“John was out of town”，似乎传达了话语的主要观点，而属性谓语，例如“Jill said that”，仅仅起到了证据或提供来源的作用(Urmson, 1952)。Simons(2007)认为，插入式阅读产生于报道与之前的话语语境之间的相互作用，而不是来自所涉及的报道的语法或语义。然而，在形式语义学中没有对这些话语相互作用的描述。在修辞结构框架下对插入语的研究产生了关于插入语语篇相互作用的假设，但这些假设在语义上并不合理。本文的目标是统一和扩展语义学和话语结构方面的工作，以发展一种正式的、基于话语的括号报告描述，而不会遭受当前修辞框架中所面临的陷阱。
{"title":"Reports in Discourse","authors":"Julie Hunter","doi":"10.5087/dad.2016.401","DOIUrl":"https://doi.org/10.5087/dad.2016.401","url":null,"abstract":"Attitude or speech reports in English with a non-parenthetical syntax sometimes give rise to interpretations in which the embedded clause, e.g., \"John was out of town\" in the report \" Jill said that John was out of town\", seems to convey the main point of the utterance while the attribution predicate, e.g., \" Jill said that\", merely plays an evidential or source-providing role (Urmson, 1952). Simons (2007) posits that parenthetical readings arise from the interaction between the report and the preceding discourse context, rather than from the syntax or semantics of the reports involved. However, no account of these discourse interactions has been developed in formal semantics. Research on parenthetical reports within frameworks of rhetorical structure has yielded hypotheses about the discourse interactions of parenthetical reports, but these hypotheses are not semantically sound. The goal of this paper is to unify and extend work in semantics and discourse structure to develop a formal, discourse-based account of parenthetical reports that does not suffer the pitfalls faced by current proposals in rhetorical frameworks.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83989305","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 a spoken dialog system, dialog state tracking refers to the task of correctly inferring the state of the conversation -- such as the user's goal -- given all of the dialog history up to that turn. Dialog state tracking is crucial to the success of a dialog system, yet until recently there were no common resources, hampering progress. The Dialog State Tracking Challenge series of 3 tasks introduced the first shared testbed and evaluation metrics for dialog state tracking, and has underpinned three key advances in dialog state tracking: the move from generative to discriminative models; the adoption of discriminative sequential techniques; and the incorporation of the speech recognition results directly into the dialog state tracker. This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled.
{"title":"The Dialog State Tracking Challenge Series: A Review","authors":"J. Williams, Antoine Raux, Matthew Henderson","doi":"10.5087/dad.2016.301","DOIUrl":"https://doi.org/10.5087/dad.2016.301","url":null,"abstract":"In a spoken dialog system, dialog state tracking refers to the task of correctly inferring the state of the conversation -- such as the user's goal -- given all of the dialog history up to that turn. Dialog state tracking is crucial to the success of a dialog system, yet until recently there were no common resources, hampering progress. The Dialog State Tracking Challenge series of 3 tasks introduced the first shared testbed and evaluation metrics for dialog state tracking, and has underpinned three key advances in dialog state tracking: the move from generative to discriminative models; the adoption of discriminative sequential techniques; and the incorporation of the speech recognition results directly into the dialog state tracker. This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82748812","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}
{"title":"Introduction to the Special Issue on Dialogue State Tracking","authors":"J. Williams, Antoine Raux, Matthew Henderson","doi":"10.5087/dad.2016.305","DOIUrl":"https://doi.org/10.5087/dad.2016.305","url":null,"abstract":"","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73774389","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}
One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges.
{"title":"Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking","authors":"Byung-Jun Lee, Kee-Eung Kim","doi":"10.5087/DAD.2016.302","DOIUrl":"https://doi.org/10.5087/DAD.2016.302","url":null,"abstract":"\u0000One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges. \u0000","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82668652","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}
F. Benamara, Nicholas Asher, Y. Mathieu, Vladimir Popescu, B. Chardon
This paper describes the CASOAR corpus, the first manually annotated corpus that explores the impact of discourse structure on sentiment analysis with a study of movie reviews in French and in English as well as letters to the editor in French. While annotating opinions at the expression, the sentence or the document level is a well-established task and relatively straightforward, discourse annotation remains diffcult, especially for non experts. Therefore, combining both annotations poses several methodological problems that we address here. We propose a multi-layered annotation scheme that includes: the complete discourse structure according to the Segmented Discourse Representation Theory, the opinion orientation of elementary discourse units and opinion expressions, and their associated features. We detail each layer, explore the interactions between them and discuss our results. In particular, we examine the correlation between discourse and semantic category of opinion expressions, the impact of discourse relations on both subjectivity and polarity analysis and the impact of discourse on the determination of the overall opinion of a document. Our results demonstrate that discourse is an important cue for sentiment analysis, at least for the corpus genres we have studied.
{"title":"Evaluation in Discourse: a Corpus-Based Study","authors":"F. Benamara, Nicholas Asher, Y. Mathieu, Vladimir Popescu, B. Chardon","doi":"10.5087/dad.2016.101","DOIUrl":"https://doi.org/10.5087/dad.2016.101","url":null,"abstract":"This paper describes the CASOAR corpus, the first manually annotated corpus that explores the impact of discourse structure on sentiment analysis with a study of movie reviews in French and in English as well as letters to the editor in French. While annotating opinions at the expression, the sentence or the document level is a well-established task and relatively straightforward, discourse annotation remains diffcult, especially for non experts. Therefore, combining both annotations poses several methodological problems that we address here. We propose a multi-layered annotation scheme that includes: the complete discourse structure according to the Segmented Discourse Representation Theory, the opinion orientation of elementary discourse units and opinion expressions, and their associated features. We detail each layer, explore the interactions between them and discuss our results. In particular, we examine the correlation between discourse and semantic category of opinion expressions, the impact of discourse relations on both subjectivity and polarity analysis and the impact of discourse on the determination of the overall opinion of a document. Our results demonstrate that discourse is an important cue for sentiment analysis, at least for the corpus genres we have studied.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80385907","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 paper introduces a type of joint utterance construction in Japanese, in which two independent sentential-level units are amalgamated, which has hitherto received little attention in the literature. Unlike traditional joint utterance construction where one speaker maintains authority over the syntactic structure of the forthcoming continuation and the other accedes to this, thereby constituting a single TCU (turn constructional unit), our examples demonstrate that both speakers can have authority over the syntactic design of joint utterances. We call such collaborative utterances ‘co-authored joint utterances’ in this paper. The uniqueness of co-authored joint utterances lies in their syntactic architecture. While syntactic and semantic continuity are successfully achieved in constructing co-authored joint utterances, they represent a co-joined structure in which two sentential-level units are involved with their shared part constituting a point of amalgamation, and because of this, the structure of a co-authored joint utterance can no longer be parsed with extant grammar. In analysing co-authored joint utterances, we examine how they can be treated in relation to the distinction between TCU (Turn Constructional Unit) continuation and new TCUs. Due to the particularities of the syntactic architecture of co-authored joint utterances, their existence raises questions about the way in which this distinction is currently operationalised, because despite being syntactically an incremental continuation, and so seemingly a TCU continuation, the co-authored joint utterance implements an action beyond what was initially instantiated by the antecedent of that joint utterance, and so arguably constitutes a new TCU.
{"title":"Co-authorship of Joint utterances in Japanese","authors":"Y. Obana, Michael Haugh","doi":"10.5087/DAD.2015.101","DOIUrl":"https://doi.org/10.5087/DAD.2015.101","url":null,"abstract":"The paper introduces a type of joint utterance construction in Japanese, in which two independent sentential-level units are amalgamated, which has hitherto received little attention in the literature. Unlike traditional joint utterance construction where one speaker maintains authority over the syntactic structure of the forthcoming continuation and the other accedes to this, thereby constituting a single TCU (turn constructional unit), our examples demonstrate that both speakers can have authority over the syntactic design of joint utterances. We call such collaborative utterances ‘co-authored joint utterances’ in this paper. \u0000The uniqueness of co-authored joint utterances lies in their syntactic architecture. While syntactic and semantic continuity are successfully achieved in constructing co-authored joint utterances, they represent a co-joined structure in which two sentential-level units are involved with their shared part constituting a point of amalgamation, and because of this, the structure of a co-authored joint utterance can no longer be parsed with extant grammar. \u0000In analysing co-authored joint utterances, we examine how they can be treated in relation to the distinction between TCU (Turn Constructional Unit) continuation and new TCUs. Due to the particularities of the syntactic architecture of co-authored joint utterances, their existence raises questions about the way in which this distinction is currently operationalised, because despite being syntactically an incremental continuation, and so seemingly a TCU continuation, the co-authored joint utterance implements an action beyond what was initially instantiated by the antecedent of that joint utterance, and so arguably constitutes a new TCU.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81321616","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}
Concession is one of the trickiest semantic discourse relations appearing in natural language. Many have tried to sub-categorize Concession and to define formal criteria to both distinguish its subtypes as well as for distinguishing Concession from the (similar) semantic relation of Contrast. But there is still a lack of consensus among the different proposals. In this paper, we focus on those approaches, e.g. Lagerwerf (1998), Winter and Rimon (1994), and Korbayova and Webber (2007), assuming that Concession features two primary interpretations, “direct” and “indirect”. We argue that this two way classification falls short of accounting for the full range of variants identified in naturally occurring data. Our investigation of one thousand Concession tokens in the Penn Discourse Treebank (PDTB) reveals that the interpretation of concessive relations varies according to the source of expectation. Four sources of expectation are identified. Each is characterized by a different relation holding between the eventuality that raises the expectation and the eventuality describing the expectation. We report a) a reliable inter-annotator agreement on the four types of sources identified in the PDTB data, b) a significant improvement on the annotation of previous disagreements on Concession-Contrast in the PDTB and c) a novel logical account of Concession using basic constructs from Hobbs (1998)’s logic. Our proposal offers a uniform framework for the interpretation of Concession while accounting for the different sources of expectation by modifying a single predicate in the proposed formulae.
{"title":"Corpus-driven Semantics of Concession: Where do Expectations Come from?","authors":"L. Robaldo, E. Miltsakaki","doi":"10.5087/dad.2014.101","DOIUrl":"https://doi.org/10.5087/dad.2014.101","url":null,"abstract":"Concession is one of the trickiest semantic discourse relations appearing in natural language. Many have tried to sub-categorize Concession and to define formal criteria to both distinguish its subtypes as well as for distinguishing Concession from the (similar) semantic relation of Contrast. But there is still a lack of consensus among the different proposals. In this paper, we focus on those approaches, e.g. Lagerwerf (1998), Winter and Rimon (1994), and Korbayova and Webber (2007), assuming that Concession features two primary interpretations, “direct” and “indirect”. We argue that this two way classification falls short of accounting for the full range of variants identified in naturally occurring data. Our investigation of one thousand Concession tokens in the Penn Discourse Treebank (PDTB) reveals that the interpretation of concessive relations varies according to the source of expectation. Four sources of expectation are identified. Each is characterized by a different relation holding between the eventuality that raises the expectation and the eventuality describing the expectation. We report a) a reliable inter-annotator agreement on the four types of sources identified in the PDTB data, b) a significant improvement on the annotation of previous disagreements on Concession-Contrast in the PDTB and c) a novel logical account of Concession using basic constructs from Hobbs (1998)’s logic. Our proposal offers a uniform framework for the interpretation of Concession while accounting for the different sources of expectation by modifying a single predicate in the proposed formulae.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77365011","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}
T. Tenbrink, K. M. Eberhard, Hui Shi, Sandra Kübler, Matthias Scheutz
Situated dialogic corpora are invaluable resources for understanding the complex relationship between language, perception, and action as they are based on naturalistic dialogue situations in which the interactants are given shared goals to be accomplished in the real world. In such situations, verbal interactions are intertwined with actions, and shared goals can only be achieved via dynamic negotiation processes based on common ground constructed from discourse history as well as the interactants' knowledge about the status of actions. In this paper, we propose four major dimensions of collaborative tasks that affect the negotiation processes among interactants, and, hence, the structure of the dialogue. Based on a review of available dialogue corpora and annotation manuals, we show that existing annotation schemes so far do not adequately account for the complex dialogue processes in situated task-based scenarios. We illustrate the effects of specific features of a scenario using annotated samples of dialogue taken from the literature as well as our own corpora, and end with a brief discussion of the challenges ahead.
{"title":"Annotation of negotiation processes in joint-action dialogues","authors":"T. Tenbrink, K. M. Eberhard, Hui Shi, Sandra Kübler, Matthias Scheutz","doi":"10.5087/DAD.2013.209","DOIUrl":"https://doi.org/10.5087/DAD.2013.209","url":null,"abstract":"Situated dialogic corpora are invaluable resources for understanding the complex relationship between language, perception, and action as they are based on naturalistic dialogue situations in which the interactants are given shared goals to be accomplished in the real world. In such situations, verbal interactions are intertwined with \u0000actions, and shared goals can only be achieved via dynamic negotiation processes based on common ground constructed from discourse history as well as the interactants' knowledge about the status of actions. In this paper, we propose four major dimensions of collaborative tasks that affect the negotiation processes among interactants, and, hence, the structure of the dialogue. Based on a review of available dialogue corpora and annotation manuals, we show that existing annotation schemes so far do not adequately account \u0000for the complex dialogue processes in situated task-based scenarios. We illustrate the effects of specific features of a scenario using annotated samples of dialogue taken from the literature as well as our own corpora, and end with a brief discussion of the challenges ahead.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77872236","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}
I present arguments in favor of the Uniformity Hypothesis: the hypothesis that discourse can extend syntax dependencies without conflicting with them. I consider arguments that Uniformity is violated in certain cases involving quotation, and I argue that the cases presented in the literature are in fact completely consistent with Uniformity. I report on an analysis of all examples in the Copenhagen Dependency Treebanks involving violations of Uniformity. I argue that they are in fact all consistent with Uniformity, and conclude that the CDT should be revised to reflect this.
{"title":"A Uniform Syntax and Discourse Structure: the Copenhagen Dependency Treebanks","authors":"D. Hardt","doi":"10.5087/DAD.2013.203","DOIUrl":"https://doi.org/10.5087/DAD.2013.203","url":null,"abstract":"I present arguments in favor of the Uniformity Hypothesis: the hypothesis that discourse can extend syntax dependencies without conflicting with them. I consider arguments that Uniformity is violated in certain cases involving quotation, and I argue that the cases \u0000presented in the literature are in fact completely consistent with Uniformity. I report on an analysis of all examples in the Copenhagen Dependency Treebanks involving violations of Uniformity. I argue that \u0000they are in fact all consistent with Uniformity, and conclude that the CDT should be revised to reflect this.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76516658","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：