Set Of Dialogues Research Articles

The Hopes and Fears Lab: enabling dialogue on discovery science

In this Practice Insight, we consider challenges associated with dialogue-based public engagement with discovery science, related to a focus on application, the need for short-term policy impact, and the lack of conceptual attention to dialogue. We consider potential responses to these through our initial evaluation of The Hopes and Fears Lab engagement project. We suggest the potential value of foregrounding emotional connections with science for both researchers and members of the public, and the need for as much attention to be paid to the preparatory work and settings for dialogue as to the dialogue itself.

Multi-modal Anaphora and Broadcasting of Information by Gestural Post-holds

This paper deals with three interrelated topics, linguistic anaphora, multi-modal anaphora and the top-down broadcasting of information using gestural post-holds in multimodal dialogue. Initially, a new solution for definite, pronominal and pro-adverbial anaphora is given based on the idea that an existentially quantified general term may output a definite reference. This approach is extended to multimodal anaphora, where part or all of an anaphor’s meaning is contributed by some sequence of iconic or deictic gestures. Anaphora exploit the semantic potential of their antecedents, they work, as tradition has it, “bottom-up”. An inverse relation, more general than cataphora, and investigated here for the first time, is “broadcasting”, where information is freely distributed top down and input to receiving sites (ports). Anaphora are modelled with the same top-down mechanism and the same applies for coherence relations in dialogue which generally show an anaphora-like behaviour. “Broadcasting” can be used in the context of anaphors, for example, to provide their gestural meaning parts but also for a verb’s multi-modal arguments for referring to a location, a direction or an area. As to multi-modal data, broadcasting is shown to be frequently tied up with gestural post-holds, the holding of a gesture’s stroke information independently of semantically alignable speech. This leads to considering post-holds from a new perspective, stressing their speech-independent function and their relevance for indicating topic-continuity. We show that multi-modal anaphora and especially broadcasting cross single contributions and turns. The data which let us develop these perspectives come from the SaGA (Speech and Gesture Alignment) corpus, a set of route-description dialogues generated in a VR-setting incorporating marker-based eye-tracking facilities. The calculus used to model the anaphora and broadcasting dynamics is the concurrent λΨ-calculus, a recently developed two-tiered machinery using a Ψ-calculus for input-output, data transport and broadcasting. The data transported are in a typed λ-calculus format incorporating Neo-Davidsonian representations; these data can be linguistic, gestural only or multi-modal. Multi-modal informational chunks are modelled as communicating agents sending and receiving information via input-output-channels. They are introduced incrementally on an empirically motivated construction or gesture-plus-construction or gesture only basis. The λΨ-calculus is also used for the multi-modal fusion component unifying gestural and linguistic information; hence, the paper is also a contribution to multi-modal fusion of linguistic and gestural input. Finally, it is shown how the presented algorithm can capture multi-modal coherence relations or a multi-modal anaphora resolution based on PTT ideas.

Samuel Beckett's Waiting for Godot and the Absurd Theatre

The research consists of three sections and conclusion. Section one deals with the idea of absurdity in the modern world has attracted many writers to thereby portray the bitter reality of a society being dominated by the discourse of modernism Section two focuses on Samuel Beckett's life and his works. In addition, Beckett places his characters in a dreamlike setting in his two-act tragicomedy Waiting for Godot (1948). The play has been criticized by a number of people; in 1953, Jacques Audiberin called it "a perfect work which deserves a triumph". Studies in Section Three Anticipating Godot as an Absurd Drama: The paper concludes with a list of references and a conclusion.. This study examines the meaning-seeking process, existentialist themes, and the human condition in Samuel Beckett's Waiting for Godot within the context of absurd theater. The play's repetitive dialogue and austere setting make it an ideal illustration of the absurdist belief that life is meaningless. The research looks at how the characters, Vladimir and Estragon, interact to show how their waiting for the illusive Godot symbolizes the pointlessness of life and the fight against hopelessness. The ridiculous routines and mutual dependence of the characters highlight the alienation and loneliness that come with living in the contemporary world. By situating Waiting for Godot in the context of Absurd Theatre, this research emphasizes Beckett's innovative use of language and structure, which challenges traditional narrative forms and invites audiences to confront the complexities of existence. Ultimately, the study reveals how Beckett's work serves as a poignant commentary on the human experience, encapsulating the essence of Absurdism through its exploration of time, identity, and hope.

Saliency infused dialogue response generation: Improving task oriented text generation using feature attribution

Challenges persist in dialogue scenarios, particularly in multi-turn dialogues where response generation often disregards contextual information beyond the last user utterance, resulting in fluent yet inadequate responses. This paper addresses these issues by identifying and resolving common shortcomings in base model responses during response generation and proposes methods to enhance response quality in unannotated dialogue settings. Our approach involves augmenting information from multiple sources, including keywords, salient features, and knowledge graph triples. We compare the effectiveness of these methods against both the base model and human annotation, which includes dialogue acts and entities. Our findings demonstrate that appending extracted tokens significantly enhances response quality compared to annotated information. In task-oriented dialogue, models perform best when infused with saliency and knowledge graph triples, as shown in the MultiWOZ dataset. Conversely, focusing solely on saliency yields better results for open-domain dialogue, as demonstrated with the DailyDialog dataset. For contextual relevance, the information infusion could also approach the performance of the LLama2 model with only a tenth of the available parameters.

Zany beetroot: architecture, autopoiesis, and the spatial formations of late capital

Using a pedagogic experiment at an architectural school in Tallinn as an empirical and conceptual starting point, this article explores the significance of autopoiesis in contemporary urban design. We suggest that organic processes—in this case the use of vegetable peels as a novel substrate—have been widely deployed in architectural discourse as a form of biomimicry. At a theoretical level these conceptual moves mark part of a wider set of dialogues between the arts and the sciences that rest on a form of degraded or even “phantom” modernism. The article draws on various insights, including the recent work of Fredric Jameson and Sianne Ngai, to explore the changing relationship between aesthetic categories and critical theory in the urban arena. We argue that aesthetic motifs derived from nature, including various forms of organicist architecture, are being effectively recycled under the aegis of late capital.

“He took her by the hand and told her to stand”

AbstractThis reflection highlights the importance of women's agency in response to crises and challenges today. The inclusion and participation of women improves the well‐being of all, be it in education, health care, the economy, or the government. There is a need to challenge interreligious dialogue settings that exclude or sideline women. Another critical area relates to the “freedom of religion or belief” agenda that sometimes concedes to misogynist perspectives in religious traditions. The text pleads strongly for full inclusion of women in the dialogue and human rights agenda.

Emotion-and-knowledge grounded response generation in an open-domain dialogue setting

The neural-based interactive dialogue system focuses on engaging and retaining humans in long-lasting conversations. This has been explored for a variety of goal-oriented dialogue domains, such as education, health care, entertainment, sports, and politics. To develop an understanding and awareness of social and cultural norms, and to address specific social skills, we need to invent strategies for building interactive systems that take into account the user’s emotions and relevant-facts in a multi-turn conversation. In this paper, we propose a new neural generative model that combines step-wise co-attention with a self-attention-based transformer network along with an emotion classifier to jointly control emotion and knowledge transfer during response generation. Quantitative, qualitative, and human evaluation results on the benchmark Topical Chat and the CMU_DoG dataset show that the proposed models can generate natural and coherent sentences, capturing essential facts with considerable improvement over emotional content.

Deliberators’ Awareness of Attitude Transformation

The significance of deliberators’ awareness of attitude transformation can be derived directly from deliberative democracy theory, but the issue has received little attention in research. This paper is an attempt to synthesize literature on factors influencing this awareness into a heuristic that can guide further inquiry. Conceptualizing learning as a fundamental mechanism through which attitudes are influenced during deliberation, either consciously or subconsciously, this heuristic stipulates that the level of awareness of any transformation is enhanced by overt persuasion in accordance with communicative rationality, and lowered, first, by various subconscious biases prompted in dialogue settings, and, second, by certain forms of calculated manipulation of deliberators. For illustrative purposes, the paper also presents a few more tangible, if tentative, observations from two small Swedish citizen dialogues that exemplify how design of deliberation may interact with factors influencing awareness of attitude transformation in real-life settings. More specifically, the observations suggest that ‘hot’ dialogues addressing well-defined and conflictual policy choices may favor awareness, while ‘colder’ consensus-oriented dialogues on broader issues might make participants less aware.

Leveraging digital methods in the quest for peaceful futures: the interplay of sincere and subjunctive technology affordances in peace mediation

ABSTRACT Efforts to support the resolution of armed conflicts through the facilitation of peace negotiations and dialogues increasingly involve digital technologies. While traditionally perceived as a human-centered activity, peace mediation now commonly entails information- and data-driven methods to enhance talks, support the analysis of conflict stakeholder needs and interests, and ground mediation efforts in better evidence. Digital technologies also promise to make peace efforts more future-oriented by helping to predict or anticipate upcoming developments, build scenarios, and increase readiness for emerging challenges. However, little is known about how such methods can be employed in dialogue and negotiation settings, where participants may have subjective and incompatible views on the conflict context, and more data and evidence don’t necessarily help to determine what a more peaceful future could look like. Through a qualitative study of the use of digitally enhanced dialogue efforts in Yemen and Libya, we demonstrate that future-oriented peacemaking requires the balancing of ‘sincere’ technology affordances that encourage an engagement with the past and present reality of conflict, with ‘subjunctive’ technology affordances that encourage an engagement with possible futures that are more peaceful. In practice, this requires combining data- and evidence-generating methods concerned with the world ‘as is’ with data analysis and visualization methods concerned with how the world ‘should’ or ‘could’ be. Our findings have implications for the study of digital methods in the facilitation of contentious political processes where the provision of data and evidence may create hurting deadlocks.

Towards the Communicative Strategies of Russian Modernism: the Poetic Correspondence of V. Bryusov and A. Bely

The object of this article is the poetic correspondence of Valery Bryusov and Andrei Bely in the 1900s. The analysis allowed us to draw a number of conclusions about the communicative strategies of Russian modernism. Firstly, in the structure of the correspondence, the dominant genre setting for dialogue with the addressee is identified, which allows identifying these poems as messages. This, on the one hand, makes it possible to fit the messages of Bryusov and Bely into the all-symbolist poetological and communicative context of the early twentieth century, when this genre was a kind of mainstream. On the other hand, the analysis of genre dominants allows us to identify their genre renewal associated with the formation of an original metastructural cycle resembling a "novel in letters", the heroes of which are Bryusov and Bely, simultaneously combining the roles of author and addressee. Secondly, in the titles of the poems under consideration ("Balder Loki", "Balder II", "Ancient Enemy", "Magician"), mythological codes are revealed, genetic links are established with Christian apocrypha and Scandinavian legends, in which the author's "I" and "you" of the addressee are associated with images of light and dark forces rooted in religious and pagan traditions. Thirdly, with the help of the biographical method, the parallels of the lyrical plots of the poems with the life and creative relationships of the poets are established. As a result, the poetic correspondence of the masters of symbolism is interpreted as a philosophical duel implicitly realizing dramatic situations of personal and "workshop" relationships, with a clear separation of aesthetic and ethical roles, these roles structure the plot of an epistolary "novel", the vicissitudes of which are reduced to binary oppositions of "light" and "darkness", heavenly and earthly, divine and demonic principles. However, at the same time, this exchange of messages appears as a dialogue about the poet's role in symbolist discourse, a dialogue reflecting different vectors of creative aspirations of symbolists and, consequently, the ambivalent tendencies of the current towards both consolidation and separation.

To repair or not to repair? Repairs and risk taking in video remote interpreting

ABSTRACT The importance of video remote interpreting (VRI) for providing interpreting services has drastically increased over the last decade. Empirical research has shown, however, that interpreting through video link may have a significant impact on the interaction and the interpreting performance in dialogue interpreting contexts. The present study contributes to this growing field of research by focusing on interpreters’ repair initiations in the context of VRI. Although repairs are an important mechanism for addressing problems in communication, very little research has been devoted to the study of interpreter-initiated repair in dialogue settings. Based on a corpus of video-recorded interpreted interactions (Dutch-Russian), where the interpreter is either present onsite or connected through video link, we analyse interpreters’ repair initiations and related risk taking behaviour. More specifically, we examine how interpreters manage a specific type of repair initiations in video remote interpreting, namely postponed repairs. The analysis reveals differences in repair patterns between video remote and onsite interpreting and we propose that these differences result from differential risk management in the two settings.

Mission Accomplished? Balancing Market Growth and Moral Legitimation in the Fair Trade Moral Market

Mission Accomplished? Balancing Market Growth and Moral Legitimation in the Fair Trade Moral Market

Audio-Visual Scenario of Kondubuleng Performance as A Learning Formula and Training of Actor

This research highlights a form of transformation of print-based scenario into audio-visual-based scenario in Kondobulengfolk theater. The urgency of this research is affected by the lack of actor regeneration of Kondobuleng folk theater so that it is one of the causes of the dimming of the theater group. In addition, the actors are known to be in a phase that is quite difficult to transfer knowledge of Kondobuleng performance, especially in the scenario. Therefore, this research provides a solution by creating a supporting media to facilitate the process of transmitting knowledge related to the scenario of Kondobuleng folk theater. As for the efforts made namely the documentation method with cinematographic technique to produce new media in the circle of performance art so as to produce academic novelty in the form of audio-visual scenario product at the Kondobuleng theater. This new media can be used as a training medium for actors in understanding plot, dialogue, texture, facial expression, and artistic set in a performance. The benefit for the Kondobuleng folk theater is a as solution to the threat of its regeneration crisis in facing the challenges of the times as well as a new spirit in restoring the existence of theater which is known to have experienced a stage crisis during the pandemic. In closing, this research has a Technology Readiness Level in terms of the use of audio-visual media in the form of scenario cinematography as a media for learning and training of actor as well as references for students in understanding scenario production techniques which are generally print-based into audio-visual-based scenario as a form of furtherance in facing the challenges of Era 5.0.

GenPADS: Reinforcing politeness in an end-to-end dialogue system.

In a task-oriented dialogue setting, user's mood and demands can change in an ongoing dialogue, which may lead to a non-informative conversation or may result in conversation drop-off. To rectify such scenarios, a conversational agent should be able to learn the user's behaviour online, and form informative, empathetic and interactive responses. To incorporate these three aspects, we propose a novel end-to-end dialogue system GenPADS. First, we build and train two models, viz. a politeness classifier to extract polite information present in user's and agent's utterances and a generation model (G) to generate varying but semantically correct responses. We then incorporate both of these models in a reinforcement learning (RL) setting using two different politeness oriented reward algorithms to adapt and generate polite responses. To train our politeness classifier, we annotate recently released Taskmaster dataset into four fine-grained classes depicting politeness and impoliteness. Further, to train our generator model, we prepare a GenDD dataset using the same Taskmaster dataset. Lastly, we train GenPADS and perform automatic and human evaluation by building seven different user simulators. Detailed analysis reveals that GenPADS performs better than the two considered baselines,viz. a transformer based seq2seq generator model for user's and agent's utterance and a retrieval based politeness adaptive dialogue system (PADS).

Hesitation Markers in Sign Language of the Netherlands A Corpus-Based Study

We present one of the first detailed studies on hesitation marking in a sign language. Based on the analysis of a set of monologues and dialogues from the Corpus NGT (Crasborn and Zwitserlood 2008; Crasborn, Zwitserlood, and Ros 2008), we describe the form and position of manual and nonmanual markers of hesitation in Sign Language of the Netherlands (NGT). We show that palm-up, used as a hesitation marker, is akin to a "filled pause" in spoken language, both in its formal properties and its distribution. palm-up is regularly used to mark hesitation in dialogues, but far less commonly in monologues, which we suggest indicates that palm-up is used deliberately by signers to signal a delay in signing (cf. e.g., Maclay and Osgood 1959). Other manual markers of hesitation include sign holds and breaks in signing; their form and patterning in the data suggest they are closer to "unfilled pauses" in speech. As for nonmanuals, we show that all instances of hesitation in our data are marked by a change in the direction of eye gaze, suggesting that this is a clear pragmatic cue that signers use—intentionally or not—to signal a planning problem in signing. This fits well with previous observations that eye gaze plays an important role in turn-taking regulation in sign languages (e.g., Baker 1977).

Dialogue Set Free?

Goldschmidt’s evocation of Leviticus 19:18 in Contradiction Set Free accomplishes heavy lifting within the distinction of the dialogic from the dialectic. Analogized to a necessary recognition of each particular and unique fulfillment of the immediate command to “love your neighbor as yourself,” dialogue is temporalized within an already near, yet not ever complete, messianic infinite. As an ongoing, active and unfinished composition of unique “nows,” dialogue’s structure is likewise epistemically distinct from the structure of dialectical synthesis. How might this distinction’s lens of Leviticus 19:18 illumine opportunities—and obstacles—for “dialogue” between humans and artificial systems? Does examining the specific case of OpenAI’s ChatGPT under the lens of Goldschmidt’s text suggest that certain questions about generative AI learning capacity might actually be questions of time?

Given-New Effects on the Duration of Gestures and of Words in Face-to-Face Dialogue

ABSTRACT The given-new contract entails that speakers must distinguish for their addressee whether references are new or already part of their dialogue. Past research had found that, in a monologue to a listener, speakers shortened repeated words. However, the notion of the given-new contract is inherently dialogic, with an addressee and the availability of co-speech gestures. Here, two face-to-face dialogue experiments tested whether gesture duration also follows the given-new contract. In Experiment 1, four experimental sequences confirmed that when speakers repeated their gestures, they shortened the duration significantly. Experiment 2 replicated the effect with spontaneous gestures in a different task. This experiment also extended earlier results with words, confirming that speakers shortened their repeated words significantly in a multimodal dialogue setting, the basic form of language use. Because words and gestures were not necessarily redundant, these results offer another instance in which gestures and words independently serve pragmatic requirements of dialogue.

Towards personalized persuasive dialogue generation for adversarial task oriented dialogue setting

In recent years, task-oriented virtual assistants have gained huge popularity and demand in both research and industry communities. The primary aim of a task-oriented dialogue agent is to assist end-users in accomplishing a task successfully and satisfactorily. Existing virtual agents have acquired proficiency in assisting users in solving simple tasks such as restaurant bookings. However, they operate under the deterministic presumption that end-users will have a servable task objective, which makes them inadequate under adversarial situations such as goal unavailability. On the other hand, human agents accomplish users’ tasks even in many goal unavailability scenarios by persuading them towards a similar goal to the user’s proposed task. Motivated by the limitation, the current work proposes and builds a novel transformer-based context-aware personalized persuasive virtual assistant (CoPersUasive VA), which also serves end-users in task unavailability situations. The proposed CoPersUasive VA recognizes goal conflicts through user sentiment and identifies an appropriate persuasion strategy using ongoing dialogue context and user personality. Depending on users’ proposed goals, it finds a similar servable goal and persuades them with the identified persuasion strategy. The obtained experimental results and detailed post-analysis firmly establish that the proposed model effectively enhances the capability of task-oriented virtual assistants to deal with the task failures caused by goal unavailability. The obtained findings also suggest the crucial role of dialogue context in identifying an appropriate and appealing persuasion strategy. The proposed CoPersUasive model could easily be adapted to any other domain by fine-tuning the model on an underlying task. Furthermore, we developed a personalized persuasive multi-intent conversational dialogue corpus annotated with intent, slot, sentiment, and dialogue act for electronic domain.22The dataset and code will be made available to accelerate research towards the development of persuasive virtual sales assistants.

Reducing Conversational Agents’ Overconfidence Through Linguistic Calibration

Abstract While improving neural dialogue agents’ factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to what extent state-of-the-art chit-chat models are linguistically calibrated in the sense that their verbalized expression of doubt (or confidence) matches the likelihood that the model’s responses are factually incorrect (or correct). We find that these models are poorly calibrated, yet we show that likelihood of correctness can accurately be predicted. By incorporating such metacognitive features into the training of a controllable generation model, we obtain a dialogue agent with greatly improved linguistic calibration.

Beyond Ethics: Considerations for Centering Equity-Minded Data Science

In this paper, we utilize duoethnography - a research method in which practitioners discursively interrogate the relationships between culture, context, and the mechanisms which shape individual autobiographical experiences - to explore what may be beyond ethics in the context of data science. Although ethical frameworks have the ability to reflect cultural priorities, a singular view of ethics, as we explore, often fails to speak to the multiple and diverse priorities held both within and across institutional spaces. To that end, this paper explores multiple perspectives, epistemologies, and worldviews that can collectively push researchers towards considerations of a data science education that is equity-minded both in concept and practice. Through a set of dialogues which examine our positionalities, journeys, ethics, local cultures, and accountabilities, this paper explores the contextual realities rooted in the authors’ educational settings. These conversations focus on the humanity of our students, the communities from which we come from and serve, as well as the unintentional harms and possibilities associated with the development of data science programs across institutional types. We take a set of five core questions to examine how we made, and continue to make, sense of our diverse cultural perspectives on data science education and equity with/in relation to others’ realities. Broadly, this paper seeks to offer reflections on the related but differing functions of ethics and equity in data science education.