Context Of Dialogue Research Articles

Symptoms are known by their companies: towards association guided disease diagnosis assistant

Over the last few years, dozens of healthcare surveys have shown a shortage of doctors and an alarming doctor-population ratio. With the motivation of assisting doctors and utilizing their time efficiently, automatic disease diagnosis using artificial intelligence is experiencing an ever-growing demand and popularity. Humans are known by the company they keep; similarly, symptoms also exhibit the association property, i.e., one symptom may strongly suggest another symptom’s existence/non-existence, and their association provides crucial information about the suffering condition. The work investigates the role of symptom association in symptom investigation and disease diagnosis process. We propose and build a virtual assistant called Association guided Symptom Investigation and Diagnosis Assistant (A-SIDA) using hierarchical reinforcement learning. The proposed A-SIDDA converses with patients and extracts signs and symptoms as per patients’ chief complaints and ongoing dialogue context. We infused association-based recommendations and critic into the assistant, which reinforces the assistant for conducting context-aware, symptom-association guided symptom investigation. Following the symptom investigation, the assistant diagnoses a disease based on the extracted signs and symptoms. The assistant then diagnoses a disease based on the extracted signs and symptoms. In addition to diagnosis accuracy, the relevance of inspected symptoms is critical to the usefulness of a diagnosis framework. We also propose a novel evaluation metric called Investigation Relevance Score (IReS), which measures the relevance of symptoms inspected during symptom investigation. The obtained improvements (Diagnosis success rate-5.36%, Dialogue length-1.16, Match rate-2.19%, Disease classifier-6.36%, IReS-0.3501, and Human score-0.66) over state-of-the-art methods firmly establish the crucial role of symptom association that gets uncovered by the virtual agent. Furthermore, we found that the association guided symptom investigation greatly increases human satisfaction, owing to its seamless topic (symptom) transition.

Children's multimodal language development from an interactional, usage-based, and cognitive perspective.

Through daily exposure to the surrounding input structured in conversations, children's language gradually develops into rich linguistic constructions that contain multiple cross-modal elements subtly used together for rich communicative functions. Children demonstrate their skills to resort to multiple semiotic resources in their daily interactions and expertly use them according to their expressive needs and communicative intents. Usage-based (Tomasello, 2003) and cognitive linguistics (Langacker, 1988) as well as construction grammar (Goldberg, 2006) have enriched our comprehension of the processes at work. Those approaches need to be combined to gesture studies (Kendon, 1988; McNeill, 1992) and multimodal approaches (Andren, 2010; Morgenstern, 2014) to fully capture the orchestration of the semiotic resources at play (Cienki, 2012; Müller, 2009). But child language development cannot be understood outside its interactional, dialogic context (Bakhtin, 1981) and without taking into account the role of expert languagers (Vygotsky, 1934) in routines or formats (Bruner, 1975). The first section thus extensively focuses on a productive combination of theoretical approaches and methods, which have been essential to understand child language development, but analyzing child language is also necessary in turn to ground socio-cognitive and interactional approaches to language. The salient features of the variably multimodal child's development are presented in the second section. The third section illustrates longitudinal pathways into multimodal languaging thanks to detailed analyses of adult-child interactive sequences. This article is categorized under: Cognitive Biology > Cognitive Development Computer Science and Robotics > Natural Language Processing Linguistics > Language Acquisition Linguistics > Cognitive Linguistics.

Olena Berehova, ‘Dialoh kul’tur: obraz inshoho v muzychnomu universumi’ [Dialogue of Cultures: The Image of the Other in the Musical Universe], Kyiv 2020

Olena Berehova’s monograph Dialoh kul’tur: obraz inshoho v muzychnomu universumi [Dialogue of Cultures: The Image of the Other in the Musical Universe] was written within the theme of basic re- search of the Institute of Cultural Studies of the National Academy of Arts of Ukraine 'Dialogue of Cultures in Postmodernity: Dynamics of Self-Organization and Globalization Challenges'. In the book, for the first time in Ukrainian culturology, an attempt is made to scientifically comprehend the dialogue of cultures through the prism of an imagological approach. The analytical material of the monograph was the latest Ukrainian composers’ creativity, as well as the best examples of contemporary world music, which are panoramic in the main musical genres (opera, ballet, symphony, vocal and choral, chamber music) and create a broad intertextual and dialogical context. In the monograph on the example of specific art cases it is proved that the imagological approach makes possible the study of artistic images objectified in works of art, revealing the specifics of figurative perception of 'Other' by different cultures, revealing the ideas of cultural dialogue about each other.

Satirical strikes and deadpanning diplomats: Stiob as geopolitical performance in Russia–US relations

AbstractThis article examines humor as geopolitical performance in the context of Russia–US political communication. Humor has featured prominently in the mass‐mediated performances of Russian state actors since 2012. Public officials such as Foreign Minister Sergey Lavrov have engaged in ambiguous play and satirical borrowings via the circulation of memes and other political theatrics. “Russiagate”—the scandal about Russian interference in the 2016 US presidential election—proved to be a particular flashpoint. I draw on recent scholarship in anthropology and media studies as well as prior ethnographic work to account for these humorous performances and consider the work that they do. Dominant analyses view this humor in militarized terms, regarding it as part of a deliberate “hybrid war” strategy. I contend that deadpanning diplomats like Lavrov are produced when a transformed Soviet‐era humorous form, stiob, intersects with a hybridized and transnationally dialogic global media context, resulting in a volatile form of geopolitical communication. In taking this state propagated humor and the confusion it generates as ethnographic objects, I contribute to anthropological interrogations of the politics of post‐truth.

Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems

A task-oriented dialogue system (TOD) is an important application of artificial intelligence. In the past few years, works on multi-domain TODs have attracted increased research attention and have seen much progress. A main challenge of such dialogue systems is finding ways to deal with cross-domain slot sharing and dialogue act temporal planning. However, existing studies seldom consider the models’ reasoning ability over the dialogue history; moreover, existing methods overlook the structure information of the ontology schema, which makes them inadequate for handling multi-domain TODs. In this paper, we present a multi-task learning framework equipped with graph attention networks (GATs) to probe the above two challenges. In the method, we explore a dialogue state GAT consisting of a dialogue context subgraph and an ontology schema subgraph to alleviate the cross-domain slot sharing issue. We further construct a GAT-enhanced memory network using the updated nodes in the ontology subgraph to filter out the irrelevant nodes to acquire the needed dialogue states. For dialogue act temporal planning, a similar GAT and corresponding memory network are proposed to obtain fine-grained dialogue act representation. Moreover, we design an entity detection task to improve the capability of soft gate, which determines whether the generated tokens are from the vocabulary or knowledge base. In the training phase, four training tasks are combined and optimized simultaneously to facilitate the response generation process. The experimental results for automatic and human evaluations show that the proposed model achieves superior results compared to the state-of-the-art models on the MultiWOZ 2.0 and MultiWOZ 2.1 datasets.

Dialogue-adaptive language model pre-training from quality estimation☆

Pre-trained language models (PrLMs) have achieved great success on a wide range of natural language processing tasks by virtue of the universal language representation ability obtained by self-supervised learning on a large corpus. These models are pre-trained on standard plain texts with general language model (LM) training objectives, which would be insufficient to model dialogue-exclusive attributes like specificity and informativeness reflected in these tasks that are not explicitly captured by the pre-trained universal language representations. In this work, we propose dialogue-adaptive pre-training objectives (DAPO) derived from quality estimation to simulate dialogue-specific features, namely coherence, specificity, and informativeness. As the foundation for model pre-training, we synthesize a new dialogue corpus and build our training set with two unsupervised methods: 1) coherence-oriented context corruption, including utterance ordering, insertion, and replacement, to help the model capture the coherence inside the dialogue contexts; and 2) specificity-oriented automatic rescoring, which encourages the model to measure the quality of the synthesized data for dialogue-adaptive pre-training by considering specificity and informativeness. Experimental results on widely used open-domain response selection and quality estimation benchmarks show that DAPO significantly improves the baseline models and achieves state-of-the-art performance on the MuTual leaderboard, verifying the effectiveness of estimating quality evaluation factors into pre-training.

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

Dialog systems have attracted attention as they are promising in many intelligent applications. Generating fluent and informative responses is of critical importance for dialog systems. Some recent studies introduce documents as extra knowledge to improve the performance of dialog generation. However, it is hard to understand the unstructured document and extract crucial information related to dialog history and current utterance. This leads to uninformative and inflexible responses in existing studies. To address this issue, we propose a generative model of a neural network with an attention mechanism for document-grounded multi-turn dialog. This model encodes the context of utterances that contains the given document, dialog history, and the last utterance into distributed representations via a triple-channel. Then, it introduces a hierarchical attention interaction between dialog contexts and previously generated utterances into the decoder for generating an appropriate response. We compare our model with various baselines on dataset CMU_DoG in terms of the evaluation criteria. The experimental results demonstrate the state-of-the-art performance of our model as compared to previous studies. Furthermore, the results of ablation experiments show the effectiveness of the hierarchical attention interaction and the triple channel for encoding. We also conduct human judgment to evaluate the informativeness of responses and the consistency of responses with dialog history.

Hard-style Selective Context Utilization for dialogue generation based on what user just said

Dialogue is a process of information exchanging, where global background is stable while local focuses are transiting. Thus, at the ongoing dialogue turn, there are both relevant and irrelevant semantics existing in dialogue contexts. How to filter out noises and selectively utilize context can pave the way to successful dialogue generation. Current work on dialogue context utilization either processes contexts as vanilla monologue text ignoring dynamic conversation flows, or depends on weighted strategies to fuse all contexts where irrelevant utterances cannot be filter out even may overwhelm relevant ones. To deal with this, this paper proposes a Hard-style Selective Context Utilization method (HardSCU). We first define and measure the information density of the last utterance (query) of a dialogue, marking it as “strong” or “weak”. For a dialogue with strong query, HardSCU directly inputs the query into a RNN-based or T5-based encoder–decoder framework to generate a response; for a dialogue with weak query, HardSCU conducts a selective context utilization for dialogue generation, where a semantic interaction module introduces relevant semantics of context to enrich the query and the co-reference relations existing in dialogue are extracted to promote the learning process of response decoder. Extensive experiments on two benchmark conversation corpora verify that our HardSCU method can outperform competitive baselines on generating appropriate responses for chit-chat-bots with yielding strong robustness to the variations of dialogue lengths.

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.

On the political theology of apartheid: a philosophical investigation

ABSTRACT This article aims to discuss the relation between political theology and apartheid critically. The relation is traced by reconsidering Carl Schmitt’s notion of political theology and the accompanying friend-enemy distinction within the South African context in dialogue with Achille Mbembe. The political theology of apartheid is accordingly analysed as the creation of a racial figure of enmity intertwined with a religious myth. Within this heuristic framework, the philosophical roots of the racial concept of the “K”-figure – as a figure of enmity – are outlined by delineating its foundations in the metaphysics of modernity with specific reference to the writings of Immanuel Kant. This concept is further considered regarding its intertwinement with the creation of the religious myth of justify Afrikaner Nationalism Volk as a chosen people of God, used to justify the Afrikaner nationalism and apartheid ideology. Finally, the opening of a space is sketched where the task of rethinking the political ontologically within a post-apartheid world may take place. The task that attempts to avoid a reconstitution of the political theology of apartheid in new figures of enmity, both religious and racial, while opening the possibility for the reparation of the dignity of those it was stolen from.

Beckett and Buddhism

Beckett and Buddhism

THE BUILDING OF A NEW LANGUAGE LEARNING MODEL BASED ON THE CHOMSKYAN CONCEPT

<p>In the light of the wide spread variety of teaching and learning methods and approaches, the building of a new Language Learning Model rises as a serious contribution that aims to surmount the problem of learning acquisition among language learners. Hence, this study comes into existence to investigate some time in such a way as to come up with some solutions on the basis of the surveyed literature in this field, especially on the basis of the Chomskyan concept of learning. By a Language Learning Model, we mean a model of learning which is based on four meaningful and required dimensions. The first one is the cross-linguistic applicability of the model to all the existing natural languages. The second one is the covering of all the cognitive and non-cognitive factors. The third one is the contextualisation of the learning factors. The fourth one is related to the process of learning and how it should take into account the three learning components, input and its richness, the students’ building competency, and communicative acts that lead to the students’ performance, in accordance with four evaluative value, quantity, quality, manner, and relation. The new conceptualized Language Learning Model is a model that helps in the activation of the learners’ expressivity in terms of creativity, adaptation, and engagement in the learning process through meaningful and comprehensible activities. A learning device that is comprehensive and instructional and that allows the learners to engage in a continuous dialogic context that enables them to learn a language by resolving the conflict between their expressivity and the limitations super-imposed by their brain.</p><p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/edu_01/0558/a.php" alt="Hit counter" /></p>

Ecological risk assessment for contaminated sites in Italy: Guidelines and path forward.

Ecological risk assessment (ERA) is defined as an iterative process that evaluates the likelihood of adverse ecological effects resulting from exposure to one or more stressors. Although ERA is recognized as a valuable procedure to better address efforts and strategies for site remediation, in Europe a common framework for the implementation of ERA in the management of contaminated sites is lacking. In Italy, there are no legally binding provisions regulating the direct assessment of potential likelihood of ecological risks. In this context, the main objective of this article was to develop a guideline to facilitate ERA application in support of an effective and sustainable management of contaminated sites in Italy and to facilitate a multistakeholder dialogue. The work was based on a critical review of existing ERA guidelines in the international context, as well as other regulatory documents and technical approaches dealing with the evaluation of ecological effects of chemical contaminants in different environmental compartments. Approaches and tools available in these documents were then used to prepare a proposed guideline for the Italian context; the proposed ERA guideline is meant to represent a flexible but robust approach that can be useful in evaluating existing data (e.g., from past investigations) as well as in the planning of site-specific investigations. To facilitate the direct application of the ERA procedure, the guideline was prepared including several templates of summary tables, checklists, and examples. The proposed ERA guideline could facilitate the decision-making process for contaminated sites with ecological values, although its application would necessarily require, at least in the initial phase, testing of its suitability to the Italian context and setting-up of a close dialogue and collaboration with local authorities and other stakeholders. Integr Environ Assess Manag 2023;19:913-919. © 2022 SETAC.

“I don’t know what you mean by `I am anxious'”: A New Method for Evaluating Conversational Agent Responses to Standardized Mental Health Inputs for Anxiety and Depression

Conversational agents (CAs) are increasingly ubiquitous and are now commonly used to access medical information. However, we lack systematic data about the quality of advice such agents provide. This paper evaluates CA advice for mental health (MH) questions, a pressing issue given that we are undergoing a mental health crisis. Building on prior work, we define a new method to systematically evaluate mental health responses from CAs. We develop multi-utterance conversational probes derived from two widely used mental health diagnostic surveys, the PHQ-9 (Depression) and the GAD-7 (Anxiety). We evaluate the responses of two text-based chatbots and four voice assistants to determine whether CAs provide relevant responses and treatments. Evaluations were conducted both by clinicians and immersively by trained raters, yielding consistent results across all raters. Although advice and recommendations were generally low quality, they were better for Crisis probes and for probes concerning symptoms of Anxiety rather than Depression. Responses were slightly improved for text versus speech-based agents, and when CAs had access to extended dialogue context. Design implications include suggestions for improved responses through clarification sub-dialogues. Responses may also be improved by the incorporation of empathy although this needs to be combined with effective treatments or advice.

Adaptive Global-Local Context Fusion for Multi-Turn Spoken Language Understanding

Recent years have seen significant advances in multi-turn Spoken Language Understanding (SLU), where dialogue contexts are used to guide intent classification and slot filling. However, how to selectively incorporate dialogue contexts, such as previous utterances and dialogue acts, into multi-turn SLU still remains a substantial challenge. In this work, we propose a novel contextual SLU model for multi-turn intent classification and slot filling tasks. We introduce an adaptive global-local context fusion mechanism to selectively integrate dialogue contexts into our model. The local context fusion aligns each dialogue context using multi-head attention, while the global context fusion measures overall context contribution to intent classification and slot filling tasks. Experiments show that on two benchmark datasets, our model achieves absolute F1 score improvements of 2.73% and 2.57% for the slot filling task on Sim-R and Sim M datasets, respectively. Additional experiments on a large-scale, de-identified, in-house dataset further verify the measurable accuracy gains of our proposed model.

Hierarchical Context Tagging for Utterance Rewriting

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences have proven stronger in both in- and out-of-domain rewriting settings. This is due to a tagger's smaller search space as it can only copy tokens from the dialogue context. However, these methods may suffer from low coverage when phrases that must be added to a source utterance cannot be covered by a single context span. This can occur in languages like English that introduce tokens such as prepositions into the rewrite for grammaticality. We propose a hierarchical context tagger (HCT) that mitigates this issue by predicting slotted rules (e.g., "besides _") whose slots are later filled with context spans. HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context. This rule tagging allows HCT to add out-of-context tokens and multiple spans at once; we further cluster the rules to truncate the long tail of the rule distribution. Experiments on several benchmarks show that HCT can outperform state-of-the-art rewriting systems by ~2 BLEU points.

Conversational emotion recognition studies based on graph convolutional neural networks and a dependent syntactic analysis

Multimodal Emotion Recognition for Conversation (ERC) is a challenging multi-class classification task that requires recognizing multiple speakers’ emotions in text, audio, video, and other modalities. ERC has received considerable attention from researchers due to its potential applications in opinion mining, advertising, and healthcare. However, the syntactic structure characteristics of the text itself have not been considered in this study. Taking into account this, this paper proposes a conversational affective analysis model (DSAGCN) combining dependent syntactic analysis and graph convolutional neural networks. Since words that reflect emotional polarity are usually concentrated exclusively in limited regions, the DSAGCN model first employs a self-attention mechanism to capture the most effective words in the dialogue context and obtain a more accurate vector representation of the emotional semantics. Then, based on speaker relationships and dependent syntactic relationships, the multimodal sentiment relationship graphs are constructed. Finally, a graph convolutional neural network is used to complete the recognition of multimodal emotion. In extensive experiments on two real datasets, IEMOCAP and MELD, the DSAGCN model outperforms the existing models in terms of average accuracy and f1 values for multimodal emotion recognition, especially for emotions such as “happiness” and “anger”. Thus, dependent syntactic analysis and self-attention mechanism can enhance the model’s ability to understand emotions.

Novel Technologies as Potential Catalyst for Democratizing Urban Heritage Preservation Practices: The Case of 3D Scanning and AI

The conflict between heritage protection and urban infrastructure development rationales creates a context for inclusion, participation and dialogue of different heritage-related communities. However, developed in the pre-computer age of administrative practice, are often incapable, partially or completely, to accommodate the ‘new-era’ community oriented participatory practices. In this article, authors discuss the mutual effects of IT in the process of democratization of urban heritage preservation. The authors create and argue the conceptual model of distributed ledger technologies (DLT) in participatory UHP. The model demonstrates how technologies can become catalysts for democratization in situations when the regulatory and administrative change (on its own) is too inert. The article hypothesizes that novel technological developments which aim at or have the potential for increasing community involvement and democratization of administrative practice, exert their effects directly through technology-based participatory practices.

CookDial: a dataset for task-oriented dialogs grounded in procedural documents

This work presents a new dialog dataset, CookDial, that facilitates research on task-oriented dialog systems with procedural knowledge understanding. The corpus contains 260 human-to-human task-oriented dialogs in which an agent, given a recipe document, guides the user to cook a dish. Dialogs in CookDial exhibit two unique features: (i) procedural alignment between the dialog flow and supporting document; (ii) complex agent decision-making that involves segmenting long sentences, paraphrasing hard instructions and resolving coreference in the dialog context. In addition, we identify three challenging (sub)tasks in the assumed task-oriented dialog system: (1) User Question Understanding, (2) Agent Action Frame Prediction, and (3) Agent Response Generation. For each of these tasks, we develop a neural baseline model, which we evaluate on the CookDial dataset. We publicly release the CookDial dataset, comprising rich annotations of both dialogs and recipe documents, to stimulate further research on domain-specific document-grounded dialog systems.

Cognitive features of indirect speech acts

ABSTRACT The offer of some cake can be declined by saying “I am on a diet” – an indirect reply. Here, we asked whether certain well-established psychological and conceptual features are linked to the (in)directness of speech acts – an issue unexplored so far. Subjects rated direct and indirect speech acts performed by the same critical linguistic forms in different dialogic contexts. We find that indirect replies were understood with less certainty, were less predictable by, less coherent with and less semantically similar to their context question. These effects were smaller when direct and indirect replies were matched for the type of speech acts for which they were used, compared to when they were not speech act matched. Crucially, all measured cognitive dimensions were strongly associated with each other. These findings suggest that indirectness goes hand-in-hand with a set of cognitive features, which should be taken into account when interpreting experimental findings, including neuroimaging studies of indirectness.