This paper describes how Rhetorical Structure Theory (RST) and relational propositions can be used to define a method for rendering and analyzing texts as expressions in propositional logic. Relational propositions, the implicit assertions that correspond to RST relations, are defined using standard logical operators and rules of inference. The resulting logical forms are used to construct logical expressions that map to RST tree structures. The resulting expressions show that inference is pervasive within coherent texts. To support reasoning over these expressions, a set of rules for negation is defined. The logical forms and their negation rules can be used to examine the flow of reasoning and the effects of incoherence. Because there is a correspondence between logical coherence and the functional relationships of RST, an RST analysis that cannot pass the test of logic is indicative either of a problematic analysis or of an incoherent text. The result is a method for analyzing the logic implicit within discursive reasoning.
{"title":"Reasoning Between the Lines: a Logic of Relational Propositions","authors":"Andrew Potter","doi":"10.5087/dad.2018.203","DOIUrl":"https://doi.org/10.5087/dad.2018.203","url":null,"abstract":"This paper describes how Rhetorical Structure Theory (RST) and relational propositions can be used to define a method for rendering and analyzing texts as expressions in propositional logic. Relational propositions, the implicit assertions that correspond to RST relations, are defined using standard logical operators and rules of inference. The resulting logical forms are used to construct logical expressions that map to RST tree structures. The resulting expressions show that inference is pervasive within coherent texts. To support reasoning over these expressions, a set of rules for negation is defined. The logical forms and their negation rules can be used to examine the flow of reasoning and the effects of incoherence. Because there is a correspondence between logical coherence and the functional relationships of RST, an RST analysis that cannot pass the test of logic is indicative either of a problematic analysis or of an incoherent text. The result is a method for analyzing the logic implicit within discursive reasoning.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78730621","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 literature on Romance null-subject languages has often postulated a division of labor between Null and Overt pronouns: Nulls prefer to retrieve an antecedent in subject position, whereas Overts prefer an antecedent in a lower syntactic position (Carminati, 2002). However, recent research on English pronouns (Rohde and Kehler, 2014) has shown grammatical function alone cannot explain pronoun interpretation. According to these models, pronoun interpretation and production are sensitive to different sets of factors and, instead of being mirror images of each other, are related probabilistically in a Bayesian fashion. This paper tests this model with Catalan data from two discourse-completion experiments to study the grammatical and pragmatic factors that affect the interpretation and production of Null and Overt pronouns. Our main result is that both Null and Overt pronouns present asymmetries regarding their interpretation and production: (1) the production of Null pronouns is affected mainly by grammatical factors (they are subject-biased), but their interpretation is also influenced by pragmatic factors (in particular, rhetorical relations), and (2) while Overt pronouns have a strong interpretation bias towards the object, the data indicates that they are not the preferred form to refer to the object.
罗曼语无主语语言的文献通常假设无主语代词和显性代词之间存在分工:无主语倾向于检索处于主语位置的先行词，而显性代词倾向于检索处于句法位置较低的先行词(Carminati, 2002)。然而，最近对英语代词的研究(Rohde and Kehler, 2014)表明，单靠语法功能并不能解释代词的解释。根据这些模型，代词的解释和产生对不同的因素集合敏感，而不是互为镜像，而是以贝叶斯方式概率相关。本文利用两个语篇完成实验的加泰罗尼亚语数据对该模型进行了检验，以研究影响虚代词和显性代词解释和产生的语法和语用因素。我们的主要结果是，Null代词和显性代词在解释和产生方面都存在不对称性:(1)Null代词的产生主要受到语法因素的影响(它们是主语偏向的)，但它们的解释也受到语用因素的影响(特别是修辞关系);(2)虽然显性代词对宾语有很强的解释偏向，但数据表明它们不是指称宾语的首选形式。
{"title":"Asymmetries between interpretation and production in Catalan pronouns","authors":"Laia Mayol","doi":"10.5087/DAD.2018.201","DOIUrl":"https://doi.org/10.5087/DAD.2018.201","url":null,"abstract":"The literature on Romance null-subject languages has often postulated a division of labor between Null and Overt pronouns: Nulls prefer to retrieve an antecedent in subject position, whereas Overts prefer an antecedent in a lower syntactic position (Carminati, 2002). However, recent research on English pronouns (Rohde and Kehler, 2014) has shown grammatical function alone cannot explain pronoun interpretation. According to these models, pronoun interpretation and production are sensitive to different sets of factors and, instead of being mirror images of each other, are related probabilistically in a Bayesian fashion. This paper tests this model with Catalan data from two discourse-completion experiments to study the grammatical and pragmatic factors that affect the interpretation and production of Null and Overt pronouns. Our main result is that both Null and Overt pronouns present asymmetries regarding their interpretation and production: (1) the production of Null pronouns is affected mainly by grammatical factors (they are subject-biased), but their interpretation is also influenced by pragmatic factors (in particular, rhetorical relations), and (2) while Overt pronouns have a strong interpretation bias towards the object, the data indicates that they are not the preferred form to refer to the object.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74778144","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}
Andrea Santana, W. Spooren, Dorien Nieuwenhuijsen, T. Sanders
Corpus-based studies in various languages have demonstrated that some connectives are used preferentially to express subjective versus objective meanings, for example, omdat vs. want in Dutch. However, Spanish connectives have been understudied from this perspective. Moreover, most of the studies of subjectivity have focused on explicit relations and little is known about the subjectivity of implicit coherence relations. In addition, the role that text type plays in the meaning and use of causal relations and their connectives is still under discussion. This study aims to analyze the local contexts of Spanish causal explicit and implicit relations in different text types by carrying out manual analyses of subjectivity. 360 relations marked by three prototypical causal connectives and 120 implicit relations were extracted from academic and journalistic texts. The analytical model applied is based on an integrative approach to subjectivity. Statistical analyses indicate a particular behavior of Spanish connectives and implicit relations and a three-way interaction between subjectivity, text type, and linguistic marking in journalistic texts. Therefore, this study reveals new insights into subjectivity in Spanish discourse.
{"title":"Subjectivity in Spanish Discourse: Explicit and Implicit Causal Relations in Different Text Types","authors":"Andrea Santana, W. Spooren, Dorien Nieuwenhuijsen, T. Sanders","doi":"10.5087/dad.2018.106","DOIUrl":"https://doi.org/10.5087/dad.2018.106","url":null,"abstract":"Corpus-based studies in various languages have demonstrated that some connectives are used preferentially to express subjective versus objective meanings, for example, omdat vs. want in Dutch. However, Spanish connectives have been understudied from this perspective. Moreover, most of the studies of subjectivity have focused on explicit relations and little is known about the subjectivity of implicit coherence relations. In addition, the role that text type plays in the meaning and use of causal relations and their connectives is still under discussion. This study aims to analyze the local contexts of Spanish causal explicit and implicit relations in different text types by carrying out manual analyses of subjectivity. 360 relations marked by three prototypical causal connectives and 120 implicit relations were extracted from academic and journalistic texts. The analytical model applied is based on an integrative approach to subjectivity. Statistical analyses indicate a particular behavior of Spanish connectives and implicit relations and a three-way interaction between subjectivity, text type, and linguistic marking in journalistic texts. Therefore, this study reveals new insights into subjectivity in Spanish discourse.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75909231","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}
Languages vary in how they encode and interpret attested information. The present research examined how users of Turkish and English construe utterances containing evidential information, in particular, whether evidential information is interpreted strictly as conveying source information (firsthand, or non-firsthand), or whether it is also perceived as signaling reliability of particular sources. Participants read sentences in their respective language presented in various source and modal forms and were asked to judge the source of information of the proposition and their confidence in whether the asserted event actually happened. It was found that there was sufficient information from evidential and modal expressions to make both source and probability of occurrence judgments, although the groups differed somewhat in their judgment patterns. The findings are taken to suggest that, for both Turkish and English speakers, evidentiality and epistemic modality overlaps to some extent but the two do not function exactly in the same way.
{"title":"Source vs. Stance: On the Relationship between Evidential and Modal Expressions","authors":"Sumeyra Tosun, Jyotsna Vaid","doi":"10.5087/dad.2018.105","DOIUrl":"https://doi.org/10.5087/dad.2018.105","url":null,"abstract":"Languages vary in how they encode and interpret attested information. The present research examined how users of Turkish and English construe utterances containing evidential information, in particular, whether evidential information is interpreted strictly as conveying source information (firsthand, or non-firsthand), or whether it is also perceived as signaling reliability of particular sources. Participants read sentences in their respective language presented in various source and modal forms and were asked to judge the source of information of the proposition and their confidence in whether the asserted event actually happened. It was found that there was sufficient information from evidential and modal expressions to make both source and probability of occurrence judgments, although the groups differed somewhat in their judgment patterns. The findings are taken to suggest that, for both Turkish and English speakers, evidentiality and epistemic modality overlaps to some extent but the two do not function exactly in the same way.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85517249","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}
Vera Cabarrão, Helena Moniz, Fernando Batista, Jaime Ferreira, I. Trancoso, Ana Isabel Mata
This paper presents an analysis of discourse markers in two spontaneous speech corpora for European Portuguese - university lectures and map-task dialogues - and also in a collection of tweets, aiming at contributing to their categorization, scarcely existent for European Portuguese. Our results show that the selection of discourse markers is domain and speaker dependent. We also found that the most frequent discourse markers are similar in all three corpora, despite tweets containing discourse markers not found in the other two corpora. In this multidisciplinary study, comprising both a linguistic perspective and a computational approach, discourse markers are also automatically discriminated from other structural metadata events, namely sentence-like units and disfluencies. Our results show that discourse markers and disfluencies tend to co-occur in the dialogue corpus, but have a complementary distribution in the university lectures. We used three acoustic-prosodic feature sets and machine learning to automatically distinguish between discourse markers, disfluencies and sentence-like units. Our in-domain experiments achieved an accuracy of about 87% in university lectures and 84% in dialogues, in line with our previous results. The eGeMAPS features, commonly used for other paralinguistic tasks, achieved a considerable performance on our data, especially considering the small size of the feature set. Our results suggest that turn-initial discourse markers are usually easier to classify than disfluencies, a result also previously reported in the literature. We conducted a cross-domain evaluation in order to evaluate the robustness of the models across domains. The results achieved are about 11%-12% lower, but we conclude that data from one domain can still be used to classify the same events in the other. Overall, despite the complexity of this task, these are very encouraging state-of-the-art results. Ultimately, using exclusively acoustic-prosodic cues, discourse markers can be fairly discriminated from disfluencies and SUs. In order to better understand the contribution of each feature, we have also reported the impact of the features in both the dialogues and the university lectures. Pitch features are the most relevant ones for the distinction between discourse markers and disfluencies, namely pitch slopes. These features are in line with the wide pitch range of discourse markers, in a continuum from a very compressed pitch range to a very wide one, expressed by total deaccented material or H+L* L* contours, with upstep H tones.
{"title":"Cross-domain analysis of discourse markers in European Portuguese","authors":"Vera Cabarrão, Helena Moniz, Fernando Batista, Jaime Ferreira, I. Trancoso, Ana Isabel Mata","doi":"10.5087/dad.2018.103","DOIUrl":"https://doi.org/10.5087/dad.2018.103","url":null,"abstract":"This paper presents an analysis of discourse markers in two spontaneous speech corpora for European Portuguese - university lectures and map-task dialogues - and also in a collection of tweets, aiming at contributing to their categorization, scarcely existent for European Portuguese. Our results show that the selection of discourse markers is domain and speaker dependent. We also found that the most frequent discourse markers are similar in all three corpora, despite tweets containing discourse markers not found in the other two corpora. In this multidisciplinary study, comprising both a linguistic perspective and a computational approach, discourse markers are also automatically discriminated from other structural metadata events, namely sentence-like units and disfluencies. Our results show that discourse markers and disfluencies tend to co-occur in the dialogue corpus, but have a complementary distribution in the university lectures. We used three acoustic-prosodic feature sets and machine learning to automatically distinguish between discourse markers, disfluencies and sentence-like units. Our in-domain experiments achieved an accuracy of about 87% in university lectures and 84% in dialogues, in line with our previous results. The eGeMAPS features, commonly used for other paralinguistic tasks, achieved a considerable performance on our data, especially considering the small size of the feature set. Our results suggest that turn-initial discourse markers are usually easier to classify than disfluencies, a result also previously reported in the literature. We conducted a cross-domain evaluation in order to evaluate the robustness of the models across domains. The results achieved are about 11%-12% lower, but we conclude that data from one domain can still be used to classify the same events in the other. Overall, despite the complexity of this task, these are very encouraging state-of-the-art results. Ultimately, using exclusively acoustic-prosodic cues, discourse markers can be fairly discriminated from disfluencies and SUs. In order to better understand the contribution of each feature, we have also reported the impact of the features in both the dialogues and the university lectures. Pitch features are the most relevant ones for the distinction between discourse markers and disfluencies, namely pitch slopes. These features are in line with the wide pitch range of discourse markers, in a continuum from a very compressed pitch range to a very wide one, expressed by total deaccented material or H+L* L* contours, with upstep H tones.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87851832","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}
L. Danlos, Katerina Rysova, Magdaléna Rysová, Manfred Stede
Starting from the perspective that discourse structure arises from the presence of coherence relations, we provide a map of linguistic discourse structuring devices (DRDs), and focus on those for written text. We propose to structure these items by differentiating between primary and secondary connectives on the one hand, and free connecting phrases on the other. For the former, we propose that their behavior can be described by lexicons, and we show one concrete proposal that by now has been applied to three languages, with others being added in ongoing work. The lexical representations can be useful both for humans (theoretical investigations, transfer to other languages) and for machines (automatic discourse parsing and generation).
{"title":"Primary and secondary discourse connectives: definitions and lexicons","authors":"L. Danlos, Katerina Rysova, Magdaléna Rysová, Manfred Stede","doi":"10.5087/DAD.2018.102","DOIUrl":"https://doi.org/10.5087/DAD.2018.102","url":null,"abstract":"Starting from the perspective that discourse structure arises from the presence of coherence relations, we provide a map of linguistic discourse structuring devices (DRDs), and focus on those for written text. We propose to structure these items by differentiating between primary and secondary connectives on the one hand, and free connecting phrases on the other. For the former, we propose that their behavior can be described by lexicons, and we show one concrete proposal that by now has been applied to three languages, with others being added in ongoing work. The lexical representations can be useful both for humans (theoretical investigations, transfer to other languages) and for machines (automatic discourse parsing and generation).","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83900572","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}
Describing implicit phenomena in discourse is known to be a problematic task, from both theoretical and empirical perspectives. The present article contributes to this topic by a novel comparative analysis of two prominent annotation approaches to discourse relations (coherence relations) that were carried out on the same texts. We compare the annotation of implicit relations in the Penn Discourse Treebank 2.0, i.e. discourse relations not signalled by an explicit discourse connective, to the recently released analysis of signals of rhetorical relations in the RST Signalling Corpus (RST-SC). The intersection of corresponding pairs of relations is rather a small one, but it shows a cleartendency: unliketheoverallsignaldistributionintheRST-SC,morethanhalfofthesignalsin the studied intersection are of semantic type, formed mostly by loosely defined lexical chains. Our data transformation allows for a simultaneous depiction and detailed study of the two resources.
{"title":"Signalling Implicit Relations: A PDTB - RST Comparison","authors":"Lucie Poláková, Jirí Mírovský, Pavlína Synková","doi":"10.5087/DAD.2017.210","DOIUrl":"https://doi.org/10.5087/DAD.2017.210","url":null,"abstract":"Describing implicit phenomena in discourse is known to be a problematic task, from both theoretical and empirical perspectives. The present article contributes to this topic by a novel comparative analysis of two prominent annotation approaches to discourse relations (coherence relations) that were carried out on the same texts. We compare the annotation of implicit relations in the Penn Discourse Treebank 2.0, i.e. discourse relations not signalled by an explicit discourse connective, to the recently released analysis of signals of rhetorical relations in the RST Signalling Corpus (RST-SC). The intersection of corresponding pairs of relations is rather a small one, but it shows a cleartendency: unliketheoverallsignaldistributionintheRST-SC,morethanhalfofthesignalsin the studied intersection are of semantic type, formed mostly by loosely defined lexical chains. Our data transformation allows for a simultaneous depiction and detailed study of the two resources.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86420761","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}
To support a natural flow of a conversation between humans and automated agents, rhetoric structures of each message has to be analyzed. We classify a pair of paragraphs of text as appropriate for one to follow another, or inappropriate, based on both topic and communicative discourse considerations. To represent a multi-sentence message with respect to how it should follow a previous message in a conversation or dialogue, we build an extension of a discourse tree for it. Extended discourse tree is based on a discourse tree for RST relations with labels for communicative actions, and also additional arcs for anaphora and ontology-based relations for entities. We refer to such trees as Communicative Discourse Trees (CDTs). We explore syntactic and discourse features that are indicative of correct vs incorrect request-response or question-answer pairs. Two learning frameworks are used to recognize such correct pairs: deterministic, nearest-neighbor learning of CDTs as graphs, and a tree kernel learning of CDTs, where a feature space of all CDT sub-trees is subject to SVM learning. We form the positive training set from the correct pairs obtained from Yahoo Answers, social network, corporate conversations including Enron emails, customer complaints and interviews by journalists. The corresponding negative training set is artificially created by attaching responses for different, inappropriate requests that include relevant keywords. The evaluation showed that it is possible to recognize valid pairs in 70% of cases in the domains of weak request-response agreement and 80% of cases in the domains of strong agreement, which is essential to support automated conversations. These accuracies are comparable with the benchmark task of classification of discourse trees themselves as valid or invalid, and also with classification of multi-sentence answers in factoid question-answering systems. The applicability of proposed machinery to the problem of chatbots, social chats and programming via NL is demonstrated. We conclude that learning rhetoric structures in the form of CDTs is the key source of data to support answering complex questions, chatbots and dialogue management.
{"title":"Discovering Rhetoric Agreement between a Request and Response","authors":"Boris A. Galitsky","doi":"10.5087/dad.2017.208","DOIUrl":"https://doi.org/10.5087/dad.2017.208","url":null,"abstract":"To support a natural flow of a conversation between humans and automated agents, rhetoric structures of each message has to be analyzed. We classify a pair of paragraphs of text as appropriate for one to follow another, or inappropriate, based on both topic and communicative discourse considerations. To represent a multi-sentence message with respect to how it should follow a previous message in a conversation or dialogue, we build an extension of a discourse tree for it. Extended discourse tree is based on a discourse tree for RST relations with labels for communicative actions, and also additional arcs for anaphora and ontology-based relations for entities. We refer to such trees as Communicative Discourse Trees (CDTs). We explore syntactic and discourse features that are indicative of correct vs incorrect request-response or question-answer pairs. Two learning frameworks are used to recognize such correct pairs: deterministic, nearest-neighbor learning of CDTs as graphs, and a tree kernel learning of CDTs, where a feature space of all CDT sub-trees is subject to SVM learning. We form the positive training set from the correct pairs obtained from Yahoo Answers, social network, corporate conversations including Enron emails, customer complaints and interviews by journalists. The corresponding negative training set is artificially created by attaching responses for different, inappropriate requests that include relevant keywords. The evaluation showed that it is possible to recognize valid pairs in 70% of cases in the domains of weak request-response agreement and 80% of cases in the domains of strong agreement, which is essential to support automated conversations. These accuracies are comparable with the benchmark task of classification of discourse trees themselves as valid or invalid, and also with classification of multi-sentence answers in factoid question-answering systems. The applicability of proposed machinery to the problem of chatbots, social chats and programming via NL is demonstrated. We conclude that learning rhetoric structures in the form of CDTs is the key source of data to support answering complex questions, chatbots and dialogue management.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88028334","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}
Ideally, the users of spoken dialogue systems should be able to speak at their own tempo. Thus, the systems needs to interpret utterances from various users correctly, even when the utterances contain pauses. In response to this issue, we propose an approach based on a posteriori restoration for incorrectly segmented utterances. A crucial part of this approach is to determine whether restoration is required. We use a classification-based approach, adapted to each user. We focus on each user’s dialogue tempo, which can be obtained during the dialogue, and determine the correlation between each user’s tempo and the appropriate thresholds for classification. A linear regression function used to convert the tempos into thresholds is also derived. Experimental results show that the proposed user adaptation approach applied to two restoration classification methods, thresholding and decision trees, improves classification accuracies by 3.0% and 7.4%, respectively, in cross validation.
{"title":"User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems","authors":"Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano","doi":"10.5087/DAD.2017.209","DOIUrl":"https://doi.org/10.5087/DAD.2017.209","url":null,"abstract":"Ideally, the users of spoken dialogue systems should be able to speak at their own tempo. Thus, the systems needs to interpret utterances from various users correctly, even when the utterances contain pauses. In response to this issue, we propose an approach based on a posteriori restoration for incorrectly segmented utterances. A crucial part of this approach is to determine whether restoration is required. We use a classification-based approach, adapted to each user. We focus on each user’s dialogue tempo, which can be obtained during the dialogue, and determine the correlation between each user’s tempo and the appropriate thresholds for classification. A linear regression function used to convert the tempos into thresholds is also derived. Experimental results show that the proposed user adaptation approach applied to two restoration classification methods, thresholding and decision trees, improves classification accuracies by 3.0% and 7.4%, respectively, in cross validation.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75008080","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}
It is generally acknowledged that discourse markers are used differently in speech and writing, yet many general descriptions and most annotation frameworks are written-based, thus partially unfit to be applied in spoken corpora. This paper identifies the major distinctive features of discourse markers in spoken language, which can be associated with problems related to their scope and structure, their meaning and their tendency to co-occur. The description is based on authentic examples and is followed by methodological recommendations on how to deal with these phenomena in more exhaustive, speech-friendly annotation models.
{"title":"Discourse Markers in Speech: Distinctive Features and Corpus Annotation","authors":"Ludivine Crible, Maria-Josep Cuenca","doi":"10.5087/dad.2017.207","DOIUrl":"https://doi.org/10.5087/dad.2017.207","url":null,"abstract":"It is generally acknowledged that discourse markers are used differently in speech and writing, yet many general descriptions and most annotation frameworks are written-based, thus partially unfit to be applied in spoken corpora. This paper identifies the major distinctive features of discourse markers in spoken language, which can be associated with problems related to their scope and structure, their meaning and their tendency to co-occur. The description is based on authentic examples and is followed by methodological recommendations on how to deal with these phenomena in more exhaustive, speech-friendly annotation models.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73256250","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：