Romualdo Ibáñez, Fernando Moncada, Benjamín Cárcamo, Valentina Marín
While some recent studies on Spanish have shown that some causal discourse markers specialize in expressing certain types of causal relations, others have revealed that causal relations may be signaled by a variety of linguistic devices. Given that we were interested not only in specificity and variety, but also in the (poly) functionality of signals, our objective in the present study was threefold. First, to identify the variety of markers used to signal causal relations in Spanish. Second, to describe the (poly) functionality of those causal markers. Third, to determine whether there exists a relationship of specificity between markers and particular types of causal relations. We analyzed a corpus of 2,514 causal coherence relations previously annotated. 40 different linguistic devices used to signal causal relations were identified. These devices were grouped into two main classes: Discourse Markers and Cue Phrases. Regarding the (poly) functionality of the markers, we found that 8 of the most frequent markers were used to signal different relations. Regarding specificity, it was observed that various conjunctions and conjunctive adverbs specialize in signaling specific relations.
{"title":"Signaling of Causal Relations in Spanish: Variety, Functionality, and Specificity","authors":"Romualdo Ibáñez, Fernando Moncada, Benjamín Cárcamo, Valentina Marín","doi":"10.5087/dad.2020.102","DOIUrl":"https://doi.org/10.5087/dad.2020.102","url":null,"abstract":"While some recent studies on Spanish have shown that some causal discourse markers specialize in expressing certain types of causal relations, others have revealed that causal relations may be signaled by a variety of linguistic devices. Given that we were interested not only in specificity and variety, but also in the (poly) functionality of signals, our objective in the present study was threefold. First, to identify the variety of markers used to signal causal relations in Spanish. Second, to describe the (poly) functionality of those causal markers. Third, to determine whether there exists a relationship of specificity between markers and particular types of causal relations. We analyzed a corpus of 2,514 causal coherence relations previously annotated. 40 different linguistic devices used to signal causal relations were identified. These devices were grouped into two main classes: Discourse Markers and Cue Phrases. Regarding the (poly) functionality of the markers, we found that 8 of the most frequent markers were used to signal different relations. Regarding specificity, it was observed that various conjunctions and conjunctive adverbs specialize in signaling specific relations.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79463889","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}
German personal and demonstrative pronouns have distinct preferences in their interpretation; personal pronouns are more flexible in their interpretation but tend to resolve to a prominent antecedent, while demonstratives have a strong preference for a non-prominent antecedent. However, less is known about how prominence information is used during the process of resolution, particularly in the light of two- stage processing models which assume that reference will normally be to the most accessible candidate. We conducted three experiments investigating how prominence information is used during the resolution of gender-disambiguated personal and demonstrative pronouns in German. While the demonstrative pronoun required additional processing compared to the personal pronoun, prominence information did not affect resolution in shallow conditions. It did, however, affect resolution under deep processing conditions. We conclude that prominence information is not ruled out by the presence of stronger resolution cues such as gender. However, the deployment of prominence information in the evaluation of candidate antecedents is under strategic control.
{"title":"The timing of prominence information during the resolution of German personal and demonstrative pronouns","authors":"Clare Patterson, P. Schumacher","doi":"10.5087/dad.2020.101","DOIUrl":"https://doi.org/10.5087/dad.2020.101","url":null,"abstract":"German personal and demonstrative pronouns have distinct preferences in their interpretation; personal pronouns are more flexible in their interpretation but tend to resolve to a prominent antecedent, while demonstratives have a strong preference for a non-prominent antecedent. However, less is known about how prominence information is used during the process of resolution, particularly in the light of two- stage processing models which assume that reference will normally be to the most accessible candidate. We conducted three experiments investigating how prominence information is used during the resolution of gender-disambiguated personal and demonstrative pronouns in German. While the demonstrative pronoun required additional processing compared to the personal pronoun, prominence information did not affect resolution in shallow conditions. It did, however, affect resolution under deep processing conditions. We conclude that prominence information is not ruled out by the presence of stronger resolution cues such as gender. However, the deployment of prominence information in the evaluation of candidate antecedents is under strategic control.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81393251","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}
Previous data-driven work investigating the types and distributions of discourse relation signals, including discourse markers such as 'however' or phrases such as 'as a result' has focused on the relative frequencies of signal words within and outside text from each discourse relation. Such approaches do not allow us to quantify the signaling strength of individual instances of a signal on a scale (e.g. more or less discourse-relevant instances of 'and'), to assess the distribution of ambiguity for signals, or to identify words that hinder discourse relation identification in context ('anti-signals' or 'distractors'). In this paper we present a data-driven approach to signal detection using a distantly supervised neural network and develop a metric, Δs (or 'delta-softmax'), to quantify signaling strength. Ranging between -1 and 1 and relying on recent advances in contextualized words embeddings, the metric represents each word's positive or negative contribution to the identifiability of a relation in specific instances in context. Based on an English corpus annotated for discourse relations using Rhetorical Structure Theory and signal type annotations anchored to specific tokens, our analysis examines the reliability of the metric, the places where it overlaps with and differs from human judgments, and the implications for identifying features that neural models may need in order to perform better on automatic discourse relation classification.
{"title":"A Neural Approach to Discourse Relation Signal Detection","authors":"Amir Zeldes, Yang Janet Liu","doi":"10.5087/dad.2020.201","DOIUrl":"https://doi.org/10.5087/dad.2020.201","url":null,"abstract":"Previous data-driven work investigating the types and distributions of discourse\u0000 relation signals, including discourse markers such as 'however' or phrases such as 'as a\u0000 result' has focused on the relative frequencies of signal words within and outside text\u0000 from each discourse relation. Such approaches do not allow us to quantify the signaling\u0000 strength of individual instances of a signal on a scale (e.g. more or less\u0000 discourse-relevant instances of 'and'), to assess the distribution of ambiguity for\u0000 signals, or to identify words that hinder discourse relation identification in context\u0000 ('anti-signals' or 'distractors'). In this paper we present a data-driven approach to\u0000 signal detection using a distantly supervised neural network and develop a metric, Δs\u0000 (or 'delta-softmax'), to quantify signaling strength. Ranging between -1 and 1 and\u0000 relying on recent advances in contextualized words embeddings, the metric represents\u0000 each word's positive or negative contribution to the identifiability of a relation in\u0000 specific instances in context. Based on an English corpus annotated for discourse\u0000 relations using Rhetorical Structure Theory and signal type annotations anchored to\u0000 specific tokens, our analysis examines the reliability of the metric, the places where\u0000 it overlaps with and differs from human judgments, and the implications for identifying\u0000 features that neural models may need in order to perform better on automatic discourse\u0000 relation classification.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75196058","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}
How does thematic role predictability affect reference production? This study tests a planning facilitation hypothesis – that the predictability effect on reference form can be explained in terms of the time course of utterance planning. In a discourse production task, participants viewed two sequential event pictures, listened to a description of the first picture (depicting a transfer event between two characters), and then provided a description of the second picture (continuing with one thematic role character, either goal or source). We replicated previous findings that goal continuations lead to more reduced forms of reference and shorter latency to begin speaking than source continuations. Additionally, we tracked speakers’ eye movements in two periods of utterance planning, early vs. late. We found that 1) early pre-planning supports the use of reduced forms but is not affected by thematic role; 2) thematic role only affects late planning; and 3) in contrast with our hypothesis, planning does not account for predictability effects on reduced forms. We then speculate that discourse connectedness drives the thematic role predictability effect on reference form choice.
{"title":"Does pre-planning explain why predictability affects reference production?","authors":"Sandra A. Zerkle, Jennifer E. Arnold","doi":"10.5087/dad.2019.202","DOIUrl":"https://doi.org/10.5087/dad.2019.202","url":null,"abstract":"How does thematic role predictability affect reference production? This study\u0000 tests a planning facilitation hypothesis – that the predictability effect on reference\u0000 form can be explained in terms of the time course of utterance planning. In a discourse\u0000 production task, participants viewed two sequential event pictures, listened to a\u0000 description of the first picture (depicting a transfer event between two characters),\u0000 and then provided a description of the second picture (continuing with one thematic role\u0000 character, either goal or source). We replicated previous findings that goal\u0000 continuations lead to more reduced forms of reference and shorter latency to begin\u0000 speaking than source continuations. Additionally, we tracked speakers’ eye movements in\u0000 two periods of utterance planning, early vs. late. We found that 1) early pre-planning\u0000 supports the use of reduced forms but is not affected by thematic role; 2) thematic role\u0000 only affects late planning; and 3) in contrast with our hypothesis, planning does not\u0000 account for predictability effects on reduced forms. We then speculate that discourse\u0000 connectedness drives the thematic role predictability effect on reference form\u0000 choice.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81675597","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 Cognitive approach to Coherence Relations (Sanders, Spooren, & Noordman, 1992) was originally proposed as a set of cognitively plausible primitives to order coherence relations, but is also increasingly used as a discourse annotation scheme. This paper provides an overview of new CCR distinctions that have been proposed over the years, summarizes the most important discussions about the operationalization of the primitives, and introduces a new distinction (disjunction) to the taxonomy to improve the descriptive adequacy of CCR. In addition, it reflects on the use of the CCR as an annotation scheme in practice. The overall aim of the paper is to provide an overview of state-of-the-art CCR for discourse annotation that can form, together with the original 1992 proposal, a comprehensive starting point for anyone interested in annotating discourse using CCR.
{"title":"Using the Cognitive Approach to Coherence Relations for Discourse Annotation","authors":"J. Hoek, J. Evers-Vermeul, T. Sanders","doi":"10.5087/DAD.2019.201","DOIUrl":"https://doi.org/10.5087/DAD.2019.201","url":null,"abstract":"The Cognitive approach to Coherence Relations (Sanders, Spooren, & Noordman,\u0000 1992) was originally proposed as a set of cognitively plausible primitives to order\u0000 coherence relations, but is also increasingly used as a discourse annotation scheme.\u0000 This paper provides an overview of new CCR distinctions that have been proposed over the\u0000 years, summarizes the most important discussions about the operationalization of the\u0000 primitives, and introduces a new distinction (disjunction) to the taxonomy to improve\u0000 the descriptive adequacy of CCR. In addition, it reflects on the use of the CCR as an\u0000 annotation scheme in practice. The overall aim of the paper is to provide an overview of\u0000 state-of-the-art CCR for discourse annotation that can form, together with the original\u0000 1992 proposal, a comprehensive starting point for anyone interested in annotating\u0000 discourse using CCR.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79193289","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 Demberg, Merel C. J. Scholman, Fatemeh Torabi Asr
Discourse-annotated corpora are an important resource for the community, but they are often annotated according to different frameworks. This makes joint usage of the annotations difficult, preventing researchers from searching the corpora in a unified way, or using all annotated data jointly to train computational systems. Several theoretical proposals have recently been made for mapping the relational labels of different frameworks to each other, but these proposals have so far not been validated against existing annotations. The two largest discourse relation annotated resources, the Penn Discourse Treebank and the Rhetorical Structure Theory Discourse Treebank, have however been annotated on the same texts, allowing for a direct comparison of the annotation layers. We propose a method for automatically aligning the discourse segments, and then evaluate existing mapping proposals by comparing the empirically observed against the proposed mappings. Our analysis highlights the influence of segmentation on subsequent discourse relation labelling, and shows that while agreement between frameworks is reasonable for explicit relations, agreement on implicit relations is low. We identify several sources of systematic discrepancies between the two annotation schemes and discuss consequences for future annotation and for usage of the existing resources.
{"title":"How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations","authors":"Vera Demberg, Merel C. J. Scholman, Fatemeh Torabi Asr","doi":"10.5087/dad.2019.104","DOIUrl":"https://doi.org/10.5087/dad.2019.104","url":null,"abstract":"Discourse-annotated corpora are an important resource for the community, but they are often annotated according to different frameworks. This makes joint usage of the annotations difficult, preventing researchers from searching the corpora in a unified way, or using all annotated data jointly to train computational systems. Several theoretical proposals have recently been made for mapping the relational labels of different frameworks to each other, but these proposals have so far not been validated against existing annotations. The two largest discourse relation annotated resources, the Penn Discourse Treebank and the Rhetorical Structure Theory Discourse Treebank, have however been annotated on the same texts, allowing for a direct comparison of the annotation layers. We propose a method for automatically aligning the discourse segments, and then evaluate existing mapping proposals by comparing the empirically observed against the proposed mappings. Our analysis highlights the influence of segmentation on subsequent discourse relation labelling, and shows that while agreement between frameworks is reasonable for explicit relations, agreement on implicit relations is low. We identify several sources of systematic discrepancies between the two annotation schemes and discuss consequences for future annotation and for usage of the existing resources.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84137409","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}
Storytelling is an integral part of daily life and a key part of how we share information and connect with others. The ability to use Natural Language Generation (NLG) to produce stories that are tailored and adapted to the individual reader could have large impact in many different applications. However, one reason that this has not become a reality to date is the NLG story gap, a disconnect between the plan-type representations that story generation engines produce, and the linguistic representations needed by NLG engines. Here we describe Fabula Tales, a storytelling system supporting both story generation and NLG. With manual annotation of texts from existing stories using an intuitive user interface, Fabula Tales automatically extracts the underlying story representation and its accompanying syntactically grounded representation. Narratological and sentence planning parameters are applied to these structures to generate different versions of the story. We show how our storytelling system can alter the story at the sentence level, as well as the discourse level. We also show that our approach can be applied to different kinds of stories by testing our approach on both Aesop’s Fables and first-person blogs posted on social media. The content and genre of such stories varies widely, supporting our claim that our approach is general and domain independent. We then conduct several user studies to evaluate the generated story variations and show that Fabula Tales’ automatically produced variations are perceived as more immediate, interesting, and correct, and are preferred to a baseline generation system that does not use narrative parameters.
{"title":"A Narrative Sentence Planner and Structurer for Domain Independent, Parameterizable Storytelling","authors":"S. Lukin, M. Walker","doi":"10.5087/DAD.2019.103","DOIUrl":"https://doi.org/10.5087/DAD.2019.103","url":null,"abstract":"Storytelling is an integral part of daily life and a key part of how we share information and connect with others. The ability to use Natural Language Generation (NLG) to produce stories that are tailored and adapted to the individual reader could have large impact in many different applications. However, one reason that this has not become a reality to date is the NLG story gap, a disconnect between the plan-type representations that story generation engines produce, and the linguistic representations needed by NLG engines. Here we describe Fabula Tales, a storytelling system supporting both story generation and NLG. With manual annotation of texts from existing stories using an intuitive user interface, Fabula Tales automatically extracts the underlying story representation and its accompanying syntactically grounded representation. Narratological and sentence planning parameters are applied to these structures to generate different versions of the story. We show how our storytelling system can alter the story at the sentence level, as well as the discourse level. We also show that our approach can be applied to different kinds of stories by testing our approach on both Aesop’s Fables and first-person blogs posted on social media. The content and genre of such stories varies widely, supporting our claim that our approach is general and domain independent. We then conduct several user studies to evaluate the generated story variations and show that Fabula Tales’ automatically produced variations are perceived as more immediate, interesting, and correct, and are preferred to a baseline generation system that does not use narrative parameters.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82217539","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}
Matthieu Riou, B. Jabaian, Stéphane Huet, F. Lefèvre
Following some recent propositions to handle natural language generation in spoken dialogue systems with long short-term memory recurrent neural network models~citep{Wen2016a} we first investigate a variant thereof with the objective of a better integration of the attention subnetwork. Then our next objective is to propose and evaluate a framework to adapt the NLG module online through direct interactions with the users. When doing so the basic way is to ask the user to utter an alternative sentence to express a particular dialogue act. But then the system has to decide between using an automatic transcription or to ask for a manual transcription. To do so a reinforcement learning approach based on an adversarial bandit scheme is retained. We show that by defining appropriately the rewards as a linear combination of expected payoffs and costs of acquiring the new data provided by the user, a system design can balance between improving the system's performance towards a better match with the user's preferences and the burden associated with it. Then the actual benefits of this system is assessed with a human evaluation, showing that the addition of more diverse utterances allows to produce sentences more satisfying for the user.
{"title":"Reinforcement adaptation of an attention-based neural natural language generator for spoken dialogue systems","authors":"Matthieu Riou, B. Jabaian, Stéphane Huet, F. Lefèvre","doi":"10.5087/DAD.2019.101","DOIUrl":"https://doi.org/10.5087/DAD.2019.101","url":null,"abstract":"Following some recent propositions to handle natural language generation in spoken dialogue systems with long short-term memory recurrent neural network models~citep{Wen2016a} we first investigate a variant thereof with the objective of a better integration of the attention subnetwork. Then our next objective is to propose and evaluate a framework to adapt the NLG module online through direct interactions with the users. When doing so the basic way is to ask the user to utter an alternative sentence to express a particular dialogue act. But then the system has to decide between using an automatic transcription or to ask for a manual transcription. To do so a reinforcement learning approach based on an adversarial bandit scheme is retained. We show that by defining appropriately the rewards as a linear combination of expected payoffs and costs of acquiring the new data provided by the user, a system design can balance between improving the system's performance towards a better match with the user's preferences and the burden associated with it. Then the actual benefits of this system is assessed with a human evaluation, showing that the addition of more diverse utterances allows to produce sentences more satisfying for the user.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85033280","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}
Gestures that co-occur with speech are a fundamental component of communication. Prior research with children suggests that gestures may help them to resolve certain forms of lexical ambiguity, including homophones. To test this idea in the context of human-robot interaction, the effects of iconic and deictic gestures on the understanding of homophones was assessed in an experiment where a humanoid robot told a short story containing pairs of homophones to small groups of young participants, accompanied by either expressive gestures or no gestures. Both groups of subjects completed a pretest and post-test to measure their ability to discriminate between pairs of homophones and we calculated aggregated precision. The results show that the use of iconic and deictic gestures aids in general understanding of homophones, providing additional evidence for the importance of gesture to the development of children’s language and communication skills.
{"title":"Using Gestures to Resolve Lexical Ambiguity in Storytelling with Humanoid Robots","authors":"S. McRoy, Catelyn Scholl","doi":"10.5087/dad.2019.102","DOIUrl":"https://doi.org/10.5087/dad.2019.102","url":null,"abstract":"Gestures that co-occur with speech are a fundamental component of communication. Prior research with children suggests that gestures may help them to resolve certain forms of lexical ambiguity, including homophones. To test this idea in the context of human-robot interaction, the effects of iconic and deictic gestures on the understanding of homophones was assessed in an experiment where a humanoid robot told a short story containing pairs of homophones to small groups of young participants, accompanied by either expressive gestures or no gestures. Both groups of subjects completed a pretest and post-test to measure their ability to discriminate between pairs of homophones and we calculated aggregated precision. The results show that the use of iconic and deictic gestures aids in general understanding of homophones, providing additional evidence for the importance of gesture to the development of children’s language and communication skills.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73594023","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 an approach to flexible and adaptive dialogue management driven by cognitive modelling of human dialogue behaviour. Artificial intelligent agents, based on the ACT-R cognitive architecture, together with human actors are participating in a (meta)cognitive skills training within a negotiation scenario. The agent employs instance-based learning to decide about its own actions and to reflect on the behaviour of the opponent. We show that task-related actions can be handled by a cognitive agent who is a plausible dialogue partner. Separating task-related and dialogue control actions enables the application of sophisticated models along with a flexible architecture in which various alternative modelling methods can be combined. We evaluated the proposed approach with users assessing the relative contribution of various factors to the overall usability of a dialogue system. Subjective perception of effectiveness, efficiency and satisfaction were correlated with various objective performance metrics, e.g. number of (in)appropriate system responses, recovery strategies, and interaction pace. It was observed that the dialogue system usability is determined most by the quality of agreements reached in terms of estimated Pareto optimality, by the user's negotiation strategies selected, and by the quality of system recognition, interpretation and responses. We compared human-human and human-agent performance with respect to the number and quality of agreements reached, estimated cooperativeness level, and frequency of accepted negative outcomes. Evaluation experiments showed promising, consistently positive results throughout the range of the relevant scales.
{"title":"Towards Integration of Cognitive Models in Dialogue Management: Designing the Virtual Negotiation Coach Application","authors":"A. Malchanau, V. Petukhova, H. Bunt","doi":"10.5087/DAD.2018.202","DOIUrl":"https://doi.org/10.5087/DAD.2018.202","url":null,"abstract":"This paper presents an approach to flexible and adaptive dialogue management driven by cognitive modelling of human dialogue behaviour. Artificial intelligent agents, based on the ACT-R cognitive architecture, together with human actors are participating in a (meta)cognitive skills training within a negotiation scenario. The agent employs instance-based learning to decide about its own actions and to reflect on the behaviour of the opponent. We show that task-related actions can be handled by a cognitive agent who is a plausible dialogue partner. Separating task-related and dialogue control actions enables the application of sophisticated models along with a flexible architecture in which various alternative modelling methods can be combined. We evaluated the proposed approach with users assessing the relative contribution of various factors to the overall usability of a dialogue system. Subjective perception of effectiveness, efficiency and satisfaction were correlated with various objective performance metrics, e.g. number of (in)appropriate system responses, recovery strategies, and interaction pace. It was observed that the dialogue system usability is determined most by the quality of agreements reached in terms of estimated Pareto optimality, by the user's negotiation strategies selected, and by the quality of system recognition, interpretation and responses. We compared human-human and human-agent performance with respect to the number and quality of agreements reached, estimated cooperativeness level, and frequency of accepted negative outcomes. Evaluation experiments showed promising, consistently positive results throughout the range of the relevant scales.","PeriodicalId":37604,"journal":{"name":"Dialogue and Discourse","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89069446","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：