Search

• Proposed an encoder–decoder for joint dialog act segmentation and recognition. • Used an attentional mechanism to integrate contextual information in dialogs. • Showed that exploiting context improves recognition accuracy. • The proposed model outperforms conventional models significantly. A dialog act represents the communicative function of an utterance in a conversation, and thus provides informative cues for understanding, managing, and generating dialog. While most spoken dialog systems process user input and system output at the turn level, a single turn can consist of multiple dialog acts in human conversations. Therefore, segmenting turn-level tokens into a meaningful dialog act unit is just as important as recognizing the dialog act. Towards joint segmentation and recognition of dialog acts, we propose an encoder–decoder model featuring joint coding and incorporate contextual information by means of an attentional mechanism. The proposed encoder–decoder outperforms other models in segmentation, and the application of attentions significantly reduces recognition error rates. By combining the encoder–decoder model with contextual attention, we achieve state-of-the-art performance in the joint evaluation of dialog act segmentation and recognition. [ABSTRACT FROM AUTHOR]

Abstract: Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system''s responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. [Copyright &y& Elsevier]

The object of the present work is an analysis of the turns that begin with tampoco. According to the principles of conversation analysis, turns and their components are not considered as isolated units of meaning, but rather in the real forms and in the sequential placements in which they appear in daily conversations. Our objective is to show that knowledge, carried out by means of the interaction, is dynamic and that tampoco is a pragma-epistemic operator with specialized (polite) meaning that contributes to the construction of the intersubjectivity. [ABSTRACT FROM AUTHOR]

Demographic research has documented the ubiquitous use of computer-mediated communication (CMC). Researchers in this area have also explored various factors associated with CMC, including uses, gratifications, motives, and needs. This investigation examines the relationships among affect for communication channels (i.e., e-mail versus face-to-face), self-reports of competence, and fear of negative evaluation. Participants (N = 325) in an undergraduate public speaking course responded to three scales, Fear of Negative Evaluation (Leary, 1983), Affect for Communication Channels Scale (Kelly & Keaten, 2007), and a measure of communication competence. Results show that individuals who reported more competence when using e-mail (27%), as compared to individuals who reported more competence face-to-face (64%), also had greater affect for CMC, higher levels of fear of negative evaluation, and reported more use of e-mail in difficult personal situations. [ABSTRACT FROM AUTHOR]

This paper presents an overview of methods that can be used to collect and analyse data on user responses to spoken dialogue system components intended to increase human-likeness, and to evaluate how well the components succeed in reaching that goal. Wizard-of-Oz variations, human-human data manipulation, and micro-domains are discussed in this context, as is the use of third-party reviewers to get a measure of the degree of human-likeness. We also present the two-way mimicry target, a model for measuring how well a human-computer dialogue mimics or replicates some aspect of human-human dialogue, including human flaws and inconsistencies. Although we have added a measure of innovation, none of the techniques is new in its entirety. Taken together and described from a human-likeness perspective, however, they form a set of tools that may widen the path towards human-like spoken dialogue systems. [Copyright &y& Elsevier]

Abstract: In this paper, we study the impact of considering context information for the annotation of emotions. Concretely, we propose the inclusion of the history of user–system interaction and the neutral speaking style of users. A new method to automatically include both sources of information has been developed making use of novel techniques for acoustic normalization and dialogue context annotation. We have carried out experiments with a corpus extracted from real human interactions with a spoken dialogue system. Results show that the performance of non-expert human annotators and machine-learned classifications are both affected by contextual information. The proposed method allows the annotation of more non-neutral emotions and yields values closer to maximum agreement rates for non-expert human annotation. Moreover, automatic classification accuracy improves by 29.57% compared to the classical approach based only on acoustic features. [Copyright &y& Elsevier]

This article compares one-dimensional and multi-dimensional dialogue act tagsets used for automatic labeling of utterances. The influence of tagset dimensionality on tagging accuracy is first discussed theoretically, then based on empirical data from human and automatic annotations of large scale resources, using four existing tagsets: damsl, swbd-damsl, icsi-mrda and maltus. The Dominant Function Approximation proposes that automatic dialogue act taggers could focus initially on finding the main dialogue function of each utterance, which is empirically acceptable and has significant practical relevance. [ABSTRACT FROM AUTHOR]

This paper reports studies on annotating and automatically detecting dialog acts in human–human spoken dialogs. The work reposes on three hypotheses: first, the succession of dialog acts is strongly constrained; second, the initial word and semantic class of word are more important for identifying dialog acts than the complete exact word sequence of an utterance; third, most of the important information is encoded in specific entities. A memory based learning approach is used to detect dialog acts. For each utterance unit, eight dialog acts are systematically annotated. Experiments have been conducted using different levels of information, with and without the use of dialog history information. In order to assess the generality of the method, the specific entity tag based model trained on a French corpus was tested on an English corpus for a similar task and on a French corpus from a different domain. A correct dialog act detection rate of about 86% is obtained for the same domain/language condition and 77% for the cross-language or cross-domain conditions. [Copyright &y& Elsevier]

This article begins with a review of second language acquisition research leading up to the 1997 article by Firth and Wagner. We argue that the Firth and Wagner article did not represent a new direction, but rather continued a type of argumentation that was already prevalent in the field at the time of the 1997 publication. We identify 3 issues as key in Firth and Wagner's argument: the scope of the research question, the multiple identities of research participants, and the context considered in research. A survey of 4 journals in the field and their treatment of these 3 issues, beginning before Firth and Wagner (1997) and leading up to the present, suggests that the article did not result in significant changes to the field and its target questions. The significance of Firth and Wagner's article lies in its licensing of situated research, and that broadening of the research base is undoubtedly positive. [ABSTRACT FROM AUTHOR]

In this article, we begin by delineating the background to and motivations behind Firth and Wagner (1997) , wherein we called for a reconceptualization of second language acquisition (SLA) research. We then outline and comment upon some of our critics' reactions to the article. Next we review and discuss the conceptual, theoretical, and methodological impact the article has had on the SLA field. Thereafter, we reengage and develop some of the themes raised but left undeveloped in the 1997 article. These themes cluster around the notions of and interrelationships between language use, language learning, and language acquisition. Although we devote space to forwarding the position that the dichotomy of language use and acquisition cannot defensibly be maintained (and in this we take up a contrary position to that held in mainstream SLA), our treatment of the issues is essentially methodological. We focus on describing a variety of aspects of learning-in-action, captured in transcripts of recordings of naturally occurring foreign, second, or other language interactions. Through transcript analyses, we explore the possibilities of describing learning-in-action devoid of cognitivistic notions of language and learning. In so doing, we advance moves to formulate and establish a reconceptualized SLA. [ABSTRACT FROM AUTHOR]

In this article, we examine parenthetical uses of honesty phrases (HPs) such as to be honest and honest to God in mundane domestic telephone calls and, for comparison, police interrogations. Parenthetical uses of HPs express a speaker's stance on the complement to which they are attached. We focus on HPs in two kinds of turn sequences: in framing dispreferred answers in question–answer (Q–A) sequences and in framing assessments. In Q–A sequences, HP+complement structures offer accounts for inability to answer in the form of reports on the speaker's intentional state (what they think, know, prefer, etc.). In assessment sequences, they frame first assessments as personal to the speaker and make relevant subsequent claims for independent, "my-side" assessments by second assessors. Generally, HPs are optional members' methods (among others) of asserting sincerity and independence as the basis of what they are saying on occasions when something functional, normative, or otherwise motivated is expectable. [ABSTRACT FROM AUTHOR]

Explores a covenant of human beings in the Third European Congress of Dialogue and Universalism. Determination of the horizons of thought and experience; Development of universalism; Essence of existence.

Focuses on the concept of the explicit performative utterances. Negation on the nature of the utterances as statements; Outline of grammatical theory; Consequences of treating explicit performative utterances as statements.

Studies a 'perspective display sequence' that attempts to cast its recipient into the role of supporter of the speaker's proposal before that proposal has been made. Preliminary strategies speakers may employ to preempt disagreement; Techniques upon which altercasting relies; Relation of self and self presentation.

Studies the nature of accounts for problematic events. Summary of how accounts are understood in some conversation analysis; Definition of accounts which elaborates on the conversation analytic approach to accounts; Four facets of accounts in problematic events; Application of approach to common problematic events.

Studies the procedures and strategies used by participants in a phone-in radio program to show their agreement or disagreement with prior talk units. Use of three agreement strategies; Significance of repetition; Verbal and non-verbal feedback.

Identifying whether an utterance is a statement, question, greeting, and so forth is integral to understanding and producing natural dialog. Human listeners easily discriminate such dialog acts (DAs) in everyday conversation, responding in systematic ways to achieve the mutual goals of the participants. Little is known, however, about how to build a fully automatic system that can successfully identify DAs occurring in natural conversation. At first blush, such a goal may appear misguided, because most current computer dialog systems are designed for human-computer interactions in specific domains. Studying unconstrained human-human dialogs would seem to make the problem more difficult than necessary, since task-oriented dialog is by definition more constrained and hence easier to process. Nevertheless, for many other applications, as well as for basic research in dialog, developing DA classifiers for conversational speech is clearly an important goal. For example, optimal automatic summarization and segmentation of natural conversations for archival and retrieval purposes requires not only knowing the string of words spoken, but also who asked questions, who answered them, whether answers were agreements or disagreements, and so forth.

Few would dispute the importance of dialogue in clinical social work practice. However, Derridean deconstruction shows how clinical dialogue can superimpose a value hierarchy, negate differences and limit understanding and action. [ABSTRACT FROM AUTHOR]

Explores the distinction between dialogue and discord. Exchange of signs; Expectation of the sender of a sign for a response from its recipient; Need of dialogue of some lack of mutual comprehension.