Context Of Dialogue Research Articles

Joint dialog act segmentation and recognition in human conversations using attention to dialog context

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.

Approaches for Dialog Management in Conversational Agents

Dialog agents, like digital assistants and automated chat interfaces (e.g., chatbots), are becoming more and more popular as users adapt to conversing with their devices as they do with humans. In this paper, we present approaches and available tools for dialog management (DM), a component of dialog agents that handles dialog context and decides the next action for the agent to take. In this paper, we establish an overview of the field of DM, compare approaches and state-of-the-art tools in industry and research work on a set of dimensions, and identify directions for further research work.

Turn-peripheral management of Common Ground: A study of Swabian gell

The present study investigates the function of the Swabian particle gell. This particle is employed to manage the Common Ground – either in a narrative or in a dialogical context. Focusing on the dialogical context, I show that gell has two intersubjective flavors: one is to request confirmation; the other is to demand it. Both flavors are available at the beginning and at the end of a turn. This is demonstrated by a quantitative analysis of the distributional behavior of the two flavors in two independent forced-choice response studies. Both flavors show an identical response pattern at both peripheries. This result is relevant for the question of whether the two turn peripheries have different discourse-functions. Under such an asymmetric perspective, turn-initial particles have a subjective meaning and turn-final particles have an intersubjective meaning (e.g. Beeching et al., 2009). Beyond a peripherally-independent meaning, the properties of gell suggest that the notion of intersubjectivity is best conceived as a matter of degree: gell has three different contexts of use, each instantiating a different degree of intersubjectivity.

Initiation, Response, Follow-up and Beyond: Analyzing Dialogue Around Difficulty in a Tutorial Setting

With the advent of Common Core-based assessments, and resulting concerns about academic achievement, more and more students may require the level of instructional intensity tutoring affords. The extent of knowledge regarding the discourse that occurs within the tutoring context is, however, limited. As a result, it is difficult to envision and implement a protocol that incorporates responsive tutor/tutee interaction. This article describes an analysis of discourse patterns that occur as a tutor responded to student difficulty. The study is framed using Bakhtin’s concept of dialogue—the ways in which interactions are influenced by the joint speaker/listener identity that is characteristic of interlocutors—and the way this played out in a dialogic instructional context. Excerpts from eight previous tutoring studies served as a foundation for the present research. The primary data source for the analysis was start-to-finish audio-recordings of 40 hours of instruction with two fourth grade readers. After preliminary open coding, overarching categories such as questioning, providing information, and demonstrating strategy use—and more detailed codes within these categories—were applied to the transcripts. Major findings demonstrated that: (a) the tutor’s moves were varied and balanced and differed somewhat from child to child, (b) some interactional sequences appeared more effective than others depending on the topic and child, and (c) interactions in this setting differed in important ways from those found in the research literature. I argue here that the dialogic characteristics of tutor/tutee interactions served the children involved and should serve as the basis for additional tutoring protocols.

End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System

Multi-role dialogue is challenging in natural language processing (NLP), which needs not only to understand sentences but also to simulate interaction among roles. However, the existing methods assume that only two speakers are present in a conversation. In real life, this assumption is not always valid. More often, there are multiple speakers involved. To address this issue, we propose a multi-role interposition dialogue system (MIDS) that generates reasonable responses based on the dialogue context and next speaker prediction. The MIDS employs multiply role-defined encoders to understand each speaker and an independent sequence model to predict the next speaker. The independent sequence model also works as a controller to integrate encoders with weights. Then, an attention-enhanced decoder generates responses based on the dialogue context, speaker prediction, and integrated encoders. Moreover, with the help of unique speaker prediction, the MIDS is able to generate diverse responses and allow itself to join (interpose) the conversation when appropriate. Furthermore, a novel reward function and an updating policy of reinforcement learning (RL) are applied to the MIDS, which further enable MIDS the ability to write drama scripts. The experimental results demonstrate that the MIDS offers a significant improvement to the accuracy of speaker prediction and the reduction of response generation perplexity. It is also able to interact with users without cues during real-life online conversations and avoid meaningless conversation loops while generating scripts. This paper marks the first step toward multi-role humorous dialogue generation.

البعد التداولي للاستفهام في الخطاب السجالي: خطاب النقائض نموذجاً

The Rhetorical Dimension of the Tri-verse Poetry Issue Poetry of contradictions (Opposition) is one of the distinctive images of the casted and sparring discourses between poets. It is a protest with an authoritative speech by excellence, in which he employs the methods of contestation,multiple and diverse methods of opposability in order to uphold the “ego” and vilify the “other”, in search of linguistic, cultural and cognitive superiority. Among the rhetorical tools employed for this purpose, we find a which is an ideal and efficient way of these discourses, which operate in a variety of ways. They are dictated by the rhetoric, the context of dialogue and the purpose of such discourse. So in this article, we will try to investigate the rhetorical dimension of the question in three-dimensional poetry (El Djarir, Farazdaq, and Alakhtal.

Social Dialogue of Employer and Employees in Poland

The aim of this paper is to investigate the (potential) impact of social dialogue on the operation of enterprises, mainly on the basis of legal provisions accompanied by practical evidence drawn from case law. This publication starts with the general context of social dialogue in the Polish legal culture. In this regard, it shows how social dialogue is defined and, in addition, it provides an overview of legal bases for social dialogue under the national rules and regulations. The remainder of the paper is structured as follows. It continues with the presentation of legal solutions regarding complex relations between various representatives of employees. In short, it explains certain aspects of the right to freedom of association. Furthermore, the article presents the special protection of employment relationship durability of employees’ representatives (as it has become a recognised field of research and scholarly enquiry) and the challenges in this area. The paper concludes with a short summary.

Міжкультурна компетентність у контексті діалогу культур

Міжкультурна компетентність у контексті діалогу культур

Augmenting Dialogue Response Generation With Unstructured Textual Knowledge

The dialogue response generation is a challenging task in chatbot applications. Recently neural-network-based dialogue models, including the sequence-to-sequence model and the RNN language models, are able to generate fluent and grammatically compliant responses, while there is a major limitation that most of the responses generated by these models are of chit-chat style instead of being informative. After investigating the currently used models, we found that one primary challenge is to model and generate informative words, such as named entities, especially when the entities have sparsely existed in training corpus. To address this problem, we propose to augment neural network-based generative architecture with knowledge embedding and knowledge attentive reader to incorporate external textual knowledge into the dialogue model to facilitate the dialogue modeling and generation. We evaluate the model with the Ubuntu dataset through automatic evaluation metrics and human evaluation. The experimental study has shown our methods outperform strong baselines in multiple metrics. We also visualize how the attention works in the dialogue context to verify the effectiveness of knowledge attentive reader mechanism.

LAS LETTERS DE JOHN TALBOT DILLON (1781) Y EL ESSAI SUR LA LITTÉRATURE ESPAGNOLE (1810) EN LOS INICIOS DE LA HISTORIOGRAFÍA LITERARIA ESPAÑOLA

Thomasina Ross advertía ya en 1823 que el Essai sur la littérature espagnole (1810), era un «gross plagiarism» de las Letters from an English traveller… (1781) de John Talbot Dillon. El presente artículo analiza la relación textual entre ambas obras, enmarcándolas en los orígenes de la historiografía literaria española. A través de una exploración de las diversas fuentes nacionales (en especial los Orígenes de Velázquez, 1754) y extranjeras utilizadas por Dillon y el autor del Essai, también se ofrecen conclusiones al respecto de: 1) cómo nacen y evolucionan las primeras historias de la literatura española en un constante diálogo que superó nuestras fronteras; 2) cómo a principios del XIX la imagen de España y su literatura vive un importante cambio en el que destacaron los viajeros británicos desde el último tercio del siglo XVIII, y el propio Dillon en particular.

Students' expressive engagement with historical film's moving images in a Maltese secondary history classroom

This paper arises from research into using historical film in a Maltese secondary history classroom vis-à-vis its impact on student motivation, engagement and historical understanding. The paper outlines and discusses indicators of students' affective and cognitive engagement when responding to and analysing historical film's moving images – that is, extracts from footage of twentieth- and twenty-first century historical events captured live on camera as shown on newsreels, broadcast on television or forming part of a historical documentary. Using a single-site study, data was collected from two cohorts of Year 11 students following the history option programme. Each cohort was taught for an academic year and moving images were used as sources in history lessons. Analysing students' discourse in whole-class dialogues to obtain evidence for student engagement, findings showed different indicators of students' expressive verbal engagement with moving images: asking questions, making spontaneous observations, inserting oneself, establishing associations, and peer interaction. Findings suggest that underlying students' expressive engagement were the visual and auditory appeal of moving images, and classroom talk. Features of classroom talk in which moving images were used were consistent with views of dialogic teaching. Based on this evidence, it is argued that moving images can be used as a tool for engaging students, through classroom talk in a dialogic context, in developing historical understanding. It is also suggested that there is potential for using students' verbal utterances when analysing moving images for assessing learning.

“Sür ve Bağla”: İngiliz Romanındaki Atlara İnsansonrası Gözlerle Bakmak

“Romanın yükselişi” hakkındaki akademik tartışmalarda çoğunlukla kabul edildiği üzere İngiliz romanının evrimi 1740ların ortasından sonra bir sıçrama yaşamıştır. Bu dönemi takip eden yüz yıllık süre içerisinde, yani 1840ların sonuna kadar, İngiliz romanı hızlı bir biçimde olgunluğa erişmiştir. Bu tarihsel dönem birçok akademisyen tarafından Antroposen çağının başlangıcı olarak kabul edilen Endüstri Devrimi’nin de tarihsel yoğunluk noktası ile neredeyse bire bir olarak örtüşmektedir. ‘Erken Antroposen Çağı’ olarak nitelendirilebilecek olan bu yüz yıllık dönemin neredeyse tam ortasında James Watt’ın buharlı lokomotifi icadı (1784) da yer almaktadır. Watt’ın icadı, o dönemde Britanya’daki insan toplumunun işaret, üretim-tüketim ve değiş-tokuş sistemlerinde insanlardan sonra en fazla eyleyici güce sahip hayvanlar olan atların yerini Viktorya Çağı’nın sonuna gelindiğinde “beygir gücü” ve “demir at”ların aldığı bir süreci başlatmıştır. Ancak, bu yüz yıllık sürede atlar sadece İngiltere’nin şehirlerinde ve kırsal bölgesinde çalışmaya devam etmekle kalmamış, aynı zamanda da İngiliz romanında “anlatısal iş yükü” taşımaya devam etmiştir. On dokuzuncu yüzyılın ortasında yaşanan Darwin Devrimi ile de bu kez insan-at ilişkilerinin ontolojik boyutlarına ilişkin algı bağlamında bir değişim yaşanmıştır. İnsanlar ve hayvanlar arasındaki ontolojik sürekliliğe ilişkin Darwinci anlayış, İngiliz romanında da yansımalarını bulmuştur. Bu arka plan üzerinde, bu makalede öncelikle Antroposen bağlamı “romanın yükselişi” tartışması ile ilişkilendirilmektedir. Daha sonra da, insansonrası bir eleştirel konumdan bakılarak, Henry Fielding’in Joseph Andrews (1742), Jane Austen’ın Northanger Manastırı (Northanger Abbey) (1818) ve Emily Brontë’nin Uğultulu Tepeler (Wuthering Heights) (1848) adlı romanlarına atıfla canlı atların “anlatısal eyleyiciliği,” George Eliot’ın Silas Marner (1861) ve Thomas Hardy’nin Tess (Tess of the d’Urbervilles) (1891) adlı romanlarına ilişkin olarak da ölü atların “anlatısal eyleyiciliği” tartışılmakta ve örneklendirilmektedir.

Adversarial training and decoding strategies for end-to-end neural conversation models

This paper presents adversarial training and decoding methods for neural conversation models that can generate natural responses given dialog contexts. In our prior work, we built several end-to-end conversation systems for the 6th Dialog System Technology Challenges (DSTC6) Twitter help-desk dialog task. These systems included novel extensions of sequence adversarial training, example-based response extraction, and Minimum Bayes-Risk based system combination. In DSTC6, our systems achieved the best performance in most objective measures such as BLEU and METEOR scores and decent performance in a subjective measure based on human rating. In this paper, we provide a complete set of our experiments for DSTC6 and further extend the training and decoding strategies more focusing on improving the subjective measure, where we combine responses of three adversarial models. Experimental results demonstrate that the extended methods improve the human rating score and outperform the best score in DSTC6.

Not Just Listening to the Teacher's Voice: A Case Study of a University English Teacher's Use of Audio Feedback on Social Media in China

A teacher’s feedback is one of the most important aspects of student learning. Although feedback can arguably move students from their current level to their desired goals, students in higher education rate it as one of the least satisfactory areas partly because of the unidirectional nature of written feedback. This paper contains a case study of a university English teacher’s use of audio feedback on a popular social media platform in China. This study includes an analysis of the teacher’s audio feedback and follow-up interactions with students on the popular WeChat application, teacher interviews, student reflective journals and 10 classroom observations of student presentations. The study found that many features of the teacher’s audio feedback contributed to student learning. Findings also reveal how the instructor’s audio feedback on social media created opportunities for dialogic feedback by increasing student engagement with the comments and enhancing meaning negotiation, as well as how the teacher and students perceive the use of audio feedback. These findings are discussed in terms of creating dialogical feedback contexts for student learning, incorporating use of audio feedback into teacher assessment literacy, and utilizing social media as an innovative platform for audio feedback. It concludes with implications for feedback practice in higher education and teacher assessment education.

Letters to anorexia. Narrative tools for working with anorectic patientsin a Dialogical Self context.

Deepening understanding of the experience of patients with anorexia nervosa in the light of a narrative-constructivist approach and Dialogic Self Theory. Exploring the phenomenon of internal dialogues, which occur in patients'minds as an interchange between two competing (healthy and disordered) aspects of their Selves. Describing diagnostic and applicative possibilities of narrative stimuli in the form of "Letters to anorexia". As was assumed the process of developing/ regaining a relative detachment from the internal voice of anorexia, which itself is indicative of progressing recovery, can be both diagnosed and fostered with externalisation techniques. Developed for the purpose of the research, a categorisation tool was designed to examine two aspects: Self-positioning (positioning above and below the voice of personified anorexia) and autobiographical narrative patterns used by researched persons. Based on statistical analysis, two different groups of patients were identified: (1) with dominant below-positioning, (2) with dominant above-positioning. Using mixed quantitative-qualitative methodology (including semantic analysis), multidimensional correlations were established within the two homogeneous clusters. Postulated in the Dialogical Self context, supporting internal dialogue in patients with anorexia nervosa seems to co-exist with subsequent stages in the treatment process, which is reflected in the letters to anorexia written during therapy. Areverse correlation can also besurmised, i.e. the positiveeffectof theintentionaltherapeutictriggering of internal dialogue and narrative experience structuring using narrative stimuli such as letters. Authors provide some suggestions for further in-depth research on internal dialogues with regard to application, diagnosis, therapy, and prevention.

Filling the gap between theory and practice: challenges from the evaluation of the Child and Family Social Work interventions and programmes

ABSTRACTThe article proposes a theoretical reflection about the evaluation field of Child and Family Social Work (CFSW) programmes and interventions. It focuses on the relationship between ways for producing knowledge through evaluation and whether and how such knowledge influence practice. In the past years, several reports have highlighted the gap between knowledge of effective treatments and practices delivered. The article aims to discuss the features of an evaluation process seeking to build a bridge between research and practice displaying the logical process by which evaluation knowledge should be rearranged in order to change practice. The value of the effort of evaluation in making generalisations and rules for helping people operate efficiently and effectively is considered. But from this view, misunderstandings about the use of the meaning of ‘science’ are identified. The author introduces a broader understanding of the ‘knowledge’ to be investigated by evaluation, no longer intended only as ‘what works’ (external evidence), but also as processes able to produce a change in people's decision-making (internal evidence) that happen within reflective and dialogical contexts (communicative evidence). These reflections are looking for a knowledge more appropriate to the CFSW field, able to improve and change practice and to ensure access to quality services.

Dialogue, ambivalence, public space

Public space is neither a fixed thing, nor a stable concept. This paper applies the term ‘dialogue’ as a conceptual basis for the idea of public space as something that changes according to multiscalar and overlapping contexts, with use and discourse. The concept of dialogue is developed from the dialogism of Mikhail Bakhtin whose related notions of ambivalence, polyphony, heteroglossia, carnival and chronotope are used to support a dialogical understanding of public space. The paper develops this understanding by creating a parallel between Bakhtin’s dialogism and the Barking Town Square by muf architecture/art (2004-2010). Through this parallel reading, the paper suggests that design proposals for the public realm are valued propositions that suggest a particular transformation of aesthetic, ethical, social and political relations through the ordering and transformation of spatial relations. No design, no conception, and therefore no dialogue creating public space can be neutral—but inevitably takes place within a fraught dialogical context inseparable from individual positioning and responsibility. The question of boundary maintenance thus arises inevitably, and the paper examines a range of such problematic demarcations, including between public and private, typologies and flexible criteria, immediate and social contexts, and ideals and reality. Given dialogue’s condition of ambivalence and incompleteness, the paper argues that the inherent contradictions to the concept of ‘public space’ are its very conditions for existence.

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models

Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response pairs. In this paper, we focus on online learning of response selection in retrieval-based dialog systems. We propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection. A bidirectional LSTM is used to produce the distributed representations of dialog context and responses, which serve as the input to a contextual bandit. In learning the bandit, we propose a customized Thompson sampling method that is applied to a polynomial feature space in approximating the reward. Experimental results on the Ubuntu Dialogue Corpus demonstrate significant performance gains of the proposed method over conventional linear contextual bandits. Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.

Assessing relevance

This paper advances an approach to relevance grounded on patterns of material inference called argumentation schemes, which can account for the reconstruction and the evaluation of relevance relations. In order to account for relevance in different types of dialogical contexts, pursuing also non-cognitive goals, and measuring the scalar strength of relevance, communicative acts are conceived as dialogue moves, whose coherence with the previous ones or the context is represented as the conclusion of steps of material inferences. Such inferences are described using argumentation schemes and are evaluated by considering (1) their defeasibility, and (2) the acceptability of the implicit premises on which they are based. The assessment of both the relevance of an utterance and the strength thereof depends on the evaluation of three interrelated factors: (1) number of inferential steps required; (2) the types of argumentation schemes involved; and (3) the implicit premises required.

Hunting the position: On the necessity of dissonance as attunement for dialogism in classroom discussion

In exploring the relationship between talk, power, and the nature of knowledge in an elementary classroom, I examine how participants position themselves and others within the tensions and dilemmas of dialogic discourse. I argue that in order to understand the complex dilemmas of enacting dialogic discourse in classrooms, power structures must be foregrounded as important theoretical and analytical constructs. Various factors contribute to the positioning of ideas and participants, including teacher question types, the polarization of ideas, and deictic pronouns across multiple layers of activity. I trace a small group discussion of a debate about the moral versus legal ethics of hunting animals in order to make the central claim that dissonance is necessary to dialogism, but it must emerge out of relations of care and the continuous effort of attunement. Despite seemingly dialogic tasks and forms as well as a desire to create dialogic contexts on the part of the teacher, authoritative meanings can pervade the learning.