Efficient Dialogue Research Articles

Benchmarking Cyber Harassment Dialogue Comprehension through Emotion-Informed Manifestations-Determinants Demarcation

In the digital age, cybercrimes, particularly cyber harassment, have become pressing issues, targeting vulnerable individuals like children, teenagers, and women. Understanding the experiences and needs of the victims is crucial for effective support and intervention. Online conversations between victims and virtual harassment counselors (chatbots) offer valuable insights into cyber harassment manifestations (CHMs) and determinants (CHDs). However, the distinction between CHMs and CHDs remains unclear. This research is the first to introduce concrete definitions for CHMs and CHDs, investigating their distinction through automated methods to enable efficient cyber-harassment dialogue comprehension. We present a novel dataset, Cyber-MaD that contains Cyber harassment dialogues manually annotated with Manifestations and Determinants. Additionally, we design an Emotion-informed Contextual Dual attention Convolution Transformer (E-ConDuCT) framework to extract CHMs and CHDs from cyber harassment dialogues. The framework primarily: a) utilizes inherent emotion features through adjective-noun pairs modeled by an autoencoder, b) employs a unique Contextual Dual attention Convolution Transformer to learn contextual insights; and c) incorporates a demarcation module leveraging task-specific emotional knowledge and a discriminator loss function to differentiate manifestations and determinants. E-ConDuCT outperforms the state-of-the-art systems on the Cyber-MaD corpus, showcasing its potential in the extraction of CHMs and CHDs. Furthermore, its robustness is demonstrated on the emotion cause extraction task using the CARES_CEASE-v2.0 dataset of suicide notes, confirming its efficacy across diverse cause extraction objectives. Access the code and data at 1. https://www.iitp.ac.in/~ai-nlp-ml/resources.html#E-ConDuCT-on-Cyber-MaD, 2. https://github.com/Soumitra816/Manifestations-Determinants.

A simple and efficient dialogue generation model incorporating commonsense knowledge

The performance of dialogue systems, artificial intelligence systems that communicate between a user and a machine, have rapidly improved owing to the development of the pre-trained language model that can perform well in various contexts. However, dialogue systems are often not well received by users because they generate universal and formulaic answers to user queries. As a result, users turn away from dialogue systems by reducing their interest in dialogue systems and lowering their expectations. To address this limitation, we propose a simple and efficient dialogue system that uses commonsense-based language models to facilitate more natural communication. Our model determines the context of human–machine conversations and then applies the relevant commonsense embedding to user queries. We quantitatively confirmed that our dialogue system performs significantly better on Korean datasets than non-commonsense-based dialogue systems.

Exploring the potential of ChatGPT in medical dialogue summarization: a study on consistency with human preferences

BackgroundTelemedicine has experienced rapid growth in recent years, aiming to enhance medical efficiency and reduce the workload of healthcare professionals. During the COVID-19 pandemic in 2019, it became especially crucial, enabling remote screenings and access to healthcare services while maintaining social distancing. Online consultation platforms have emerged, but the demand has strained the availability of medical professionals, directly leading to research and development in automated medical consultation. Specifically, there is a need for efficient and accurate medical dialogue summarization algorithms to condense lengthy conversations into shorter versions focused on relevant medical facts. The success of large language models like generative pre-trained transformer (GPT)-3 has recently prompted a paradigm shift in natural language processing (NLP) research. In this paper, we will explore its impact on medical dialogue summarization.MethodsWe present the performance and evaluation results of two approaches on a medical dialogue dataset. The first approach is based on fine-tuned pre-trained language models, such as bert-based summarization (BERTSUM) and bidirectional auto-regressive Transformers (BART). The second approach utilizes a large language models (LLMs) GPT-3.5 with inter-context learning (ICL). Evaluation is conducted using automated metrics such as ROUGE and BERTScore.ResultsIn comparison to the BART and ChatGPT models, the summaries generated by the BERTSUM model not only exhibit significantly lower ROUGE and BERTScore values but also fail to pass the testing for any of the metrics in manual evaluation. On the other hand, the BART model achieved the highest ROUGE and BERTScore values among all evaluated models, surpassing ChatGPT. Its ROUGE-1, ROUGE-2, ROUGE-L, and BERTScore values were 14.94%, 53.48%, 32.84%, and 6.73% higher respectively than ChatGPT’s best results. However, in the manual evaluation by medical experts, the summaries generated by the BART model exhibit satisfactory performance only in the “Readability” metric, with less than 30% passing the manual evaluation in other metrics. When compared to the BERTSUM and BART models, the ChatGPT model was evidently more favored by human medical experts.ConclusionOn one hand, the GPT-3.5 model can manipulate the style and outcomes of medical dialogue summaries through various prompts. The generated content is not only better received than results from certain human experts but also more comprehensible, making it a promising avenue for automated medical dialogue summarization. On the other hand, automated evaluation mechanisms like ROUGE and BERTScore fall short in fully assessing the outputs of large language models like GPT-3.5. Therefore, it is necessary to research more appropriate evaluation criteria.

Patient decision-making in the era of transcarotid artery revascularization

ObjectiveThe National Coverage Determination on carotid stenting by Medicare in October 2023 stipulates that patients participate in a shared decision-making (SDM) conversation with their proceduralist before an intervention. However, to date, there is no validated SDM tool that incorporates transcarotid artery revascularization (TCAR) into its decision platform. Our objective was to elicit patient and surgeon experiences and preferences through a qualitative approach to better inform the SDM process surrounding carotid revascularization. MethodsWe performed longitudinal perioperative semistructured interviews of 20 participants using purposive maximum variation sampling, a qualitative technique designed for identification and selection of information-rich cases, to define domains important to participants undergoing carotid endarterectomy or TCAR and impressions of SDM. We also performed interviews with nine vascular surgeons to elicit their input on the SDM process surrounding carotid revascularization. Interview data were coded and analyzed using inductive content analysis coding. ResultsWe identified three important domains that contribute to the participants' ultimate decision on which procedure to choose: their individual values, their understanding of the disease and each procedure, and how they prefer to make medical decisions. Participant values included themes such as success rates, “wanting to feel better,” and the proceduralist's experience. Participants varied in their desired degree of understanding of carotid disease, but all individuals wished to discuss each option with their proceduralist. Participants' desired medical decision-making style varied on a spectrum from complete autonomy to wanting the proceduralist to make the decision for them. Participants who preferred carotid endarterectomy felt outcomes were superior to TCAR and often expressed a desire to eliminate the carotid plaque. Those selecting TCAR felt it was a newer, less invasive option with the shortest procedural and recovery times. Surgeons frequently noted patient factors such as age and anatomy, as well as the availability of long-term data, as reasons to preferentially select one procedure. For most participants, their surgeon was viewed as the most important source of information surrounding their disease and procedure. ConclusionsSDM surrounding carotid revascularization is nuanced and marked by variation in patient preferences surrounding autonomy when choosing treatment. Given the mandate by Medicare to participate in a SDM interaction before carotid stenting, this analysis offers critical insights that can help to guide an efficient and effective dialog between patients and providers to arrive at a shared decision surrounding therapeutic intervention for patients with carotid disease.

DSTEA: Improving Dialogue State Tracking via Entity Adaptive pre-training

Dialogue State Tracking (DST) is critical for comprehensively interpreting user and system utterances, thereby forming the cornerstone of efficient dialogue systems. Despite past research efforts focused on enhancing DST performance through alterations to the model structure or integrating additional features like graph relations, they often require additional pre-training with external dialogue corpora. In this study, we propose DSTEA, improving Dialogue State Tracking via Entity Adaptive pre-training, which can enhance the encoder through by intensively training key entities in dialogue utterances. DSTEA identifies these pivotal entities from input dialogues utilizing four different methods: ontology information, named-entity recognition, the spaCy toolkit, and the flair library. Subsequently, it employs selective knowledge masking to train the model effectively. Remarkably, DSTEA only requires pre-training without the direct infusion of extra knowledge into the DST model. This approach results in substantial performance improvements of four robust DST models on MultiWOZ 2.0, 2.1, and 2.2, with joint goal accuracy witnessing an increase of up to 2.69% (from 52.41% to 55.10%). Comparative experiments considering various entity types and different entity adaptive pre-training configurations, such as masking strategy and masking rate, further validated the efficacy of DSTEA.

A Temporal Variable-Scale Clustering Method on Feature Identification for Policy Public-Opinion Management

The development of various digital social network platforms has caused public opinion to play an increasingly important role in the policy making process. However, due to the fact that public opinion hotspots usually change rapidly (such as the phenomenon of public opinion inversion), both the behaviour feature and demand feature of netizens included in the public opinion often vary over time. Therefore, this paper focuses on the feature identification problem of public opinion simultaneously considering the multiple observation time intervals and key time points, in order to support the management of policy-focused online public opinion. According to the variable-scale data analysis theory, the temporal scale space model is established to describe candidate temporal observation scales, which are organized following the time points of relevant policy promulgation (policy time points). After proposing the multi-scale temporal data model, a temporal variable-scale clustering method (T-VSC) is put forward. Compared to the traditional numerical variable-scale clustering method, the proposed T-VSC enables to combine the subjective attention of decision-makers and objective timeliness of public opinion data together during the scale transformation process. The case study collects 48552 raw public opinion data on the double-reduction education policy from Sina Weibo platform during Jan 2023 to Nov 2023. Experimental results indicate that the proposed T-VSC method could divide netizens that participate in the dissemination of policy-focused public opinion into clusters with low behavioural granularity deviation on the satisfied observation time scales, and identify the differentiated demand feature of each netizen cluster at policy time points, which could be applied to build the timely and efficient digital public dialogue mechanism.

Natural Language-Driven Dialogue Systems for Support in Physical Medicine and Rehabilitation

This paper presents a natural language-driven dialogue system designed to support healthcare professionals and students in the field of physical medicine and rehabilitation. The system seamlessly integrates concepts from intelligent information systems, data mining, ontologies, and human-computer interaction, employing at its core a rule-based dialogue mechanism. The system harnesses the power of ontology-based graph knowledge, underscoring its domain-specific efficacy. This article delves into the automated knowledge base formation, utilising Python scripts to translate EBSCO’s dataset of articles on physical medicine and rehabilitation into an OWL ontology. This methodology ensures adaptability to the ever-evolving landscape of medical insights. The system’s approach to natural language processing encompasses text preprocessing, semantic category discernment, andSPARQL query creation, providing 26 predefined categories. As an innovation in performance optimisation, the system integrates a strategy to cache precomputed responses using a PostgreSQL database, which aids in resource conservation and reduction in query execution latency. The system’s user engagement avenues are further detailed, showcasing a Telegram bot and an API, enhancing accessibility and user experience. In essence, this article illuminates an advanced, efficient dialogue system for physical medicine and rehabilitation, synthesising multiple computational paradigms, and standing as a beacon for healthcare practitioners and students alike.

Exploring emotions in Bach chorales: a multi-modal perceptual and data-driven study.

The relationship between music and emotion has been addressed within several disciplines, from more historico-philosophical and anthropological ones, such as musicology and ethnomusicology, to others that are traditionally more empirical and technological, such as psychology and computer science. Yet, understanding the link between music and emotion is limited by the scarce interconnections between these disciplines. Trying to narrow this gap, this data-driven exploratory study aims at assessing the relationship between linguistic, symbolic and acoustic features-extracted from lyrics, music notation and audio recordings-and perception of emotion. Employing a listening experiment, statistical analysis and unsupervised machine learning, we investigate how a data-driven multi-modal approach can be used to explore the emotions conveyed by eight Bach chorales. Through a feature selection strategy based on a set of more than 300 Bach chorales and a transdisciplinary methodology integrating approaches from psychology, musicology and computer science, we aim to initiate an efficient dialogue between disciplines, able to promote a more integrative and holistic understanding of emotions in music.

Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches, and Future Directions

Abstractive dialogue summarization generates a concise and fluent summary covering the salient information in a dialogue among two or more interlocutors. It has attracted significant attention in recent years based on the massive emergence of social communication platforms and an urgent requirement for efficient dialogue information understanding and digestion. Different from news or articles in traditional document summarization, dialogues bring unique characteristics and additional challenges, including different language styles and formats, scattered information, flexible discourse structures, and unclear topic boundaries. This survey provides a comprehensive investigation of existing work for abstractive dialogue summarization from scenarios, approaches to evaluations. It categorizes the task into two broad categories according to the type of input dialogues, i.e., open-domain and task-oriented, and presents a taxonomy of existing techniques in three directions, namely, injecting dialogue features, designing auxiliary training tasks, and using additional data. A list of datasets under different scenarios and widely accepted evaluation metrics are summarized for completeness. After that, the trends of scenarios and techniques are summarized, together with deep insights into correlations between extensively exploited features and different scenarios. Based on these analyses, we recommend future directions, including more controlled and complicated scenarios, technical innovations and comparisons, publicly available datasets in special domains, and so on.

Efficient fault-tolerant quantum dialogue protocols using a quantum reordering circuit of EPR pairs

This study proposes two efficient fault-tolerant quantum dialogue (QD) protocols that are robust against the collective-dephasing and collective-rotation noises, respectively. In the proposed protocol, the message carriers are decoherence-free quantum states that are resistant to the corresponding collective noise, provided that all quantum photon pairs of a transmitted unit remain within the same time window. These quantum states and their combinations are used to compose the decoy photon pairs to ensure the security of the transmission. An observation on the Bell measurement has allowed an EPR pair as a message carrier to Require only one of its photons for protection. That is, the measurement of one single photon in an EPR pair will gain no information on its actual Bell state. This property has effectively reduced the number of decoy photons in quantum transmission. Since the photons used in the message carriers are particles of EPR pairs, the proposed two fault-tolerant QD protocols required only half of the decoy photons to ensure the same level of security. In the transmission, one photon of each EPR pair is separated using a reordering mechanism, and a quantum logic circuit is designed and implemented to demonstrate the concept in practice. The reduction of decoy photons has significantly improved the qubit efficiency of the proposed QD protocols compared with other relevant existing works. Furthermore, the proposed schemes also have no information leakage problem.

Internalization of Islamic Moderation Values in Building a Civilization of Love and Tolerance

The purpose of this research is to obtain information about the pattern of internalization of Islamic moderation values in building a civilization of love and tolerance by harbouring all the differences that can create hostility and disharmony amid a pluralistic social life. This research is library research because all the data used as material for conducting studies comes from texts or manuscripts that have become library collections using qualitative research methods and analyzed with the nature of descriptive analytic studies. The results of this study state that Islamic moderation values in their implementation in social life as an effort to prevent various extremist, fundamentalist, liberal and radical understandings that are very far from Islamic teachings, which are full of love and tolerance. Love and tolerance are important provisions in forming civilization in a harmonious religious life without any conflict due to diversity. Love can also foster harmony in religious, national and state life, thus creating peace in society. Love makes a person have good morals who always want peace so that he always pleases others in every word and behaviour. Meanwhile, with better tolerance, constructive and efficient dialogue will be built, which can foster religious attitudes and an atmosphere that is more open, plural, and inclusive.

Internalization of Islamic Moderation Values in Building a Civilization of Love and Tolerance

The purpose of this research is to obtain information about the pattern of internalization of Islamic moderation values in building a civilization of love and tolerance by harbouring all the differences that can create hostility and disharmony amid a pluralistic social life. This research is library research because all the data used as material for conducting studies comes from texts or manuscripts that have become library collections using qualitative research methods and analyzed with the nature of descriptive analytic studies. The results of this study state that Islamic moderation values in their implementation in social life as an effort to prevent various extremist, fundamentalist, liberal and radical understandings that are very far from Islamic teachings, which are full of love and tolerance. Love and tolerance are important provisions in forming civilization in a harmonious religious life without any conflict due to diversity. Love can also foster harmony in religious, national and state life, thus creating peace in society. Love makes a person have good morals who always want peace so that he always pleases others in every word and behaviour. Meanwhile, with better tolerance, constructive and efficient dialogue will be built, which can foster religious attitudes and an atmosphere that is more open, plural, and inclusive.

Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy

Achieving high performance in a multi-domain dialogue system with low computation is undoubtedly challenging. Previous works applying an end-to-end approach have been very successful. However, the computational cost remains a major issue since the large-sized language model using GPT-2 is required. Meanwhile, the optimization for individual components in the dialogue system has not shown promising result, especially for the component of dialogue management due to the complexity of multi-domain state and action representation. To cope with these issues, this article presents an efficient guidance learning where the imitation learning and the hierarchical reinforcement learning (HRL) with human-in-the-loop are performed to achieve high performance via an inexpensive dialogue agent. The behavior cloning with auxiliary tasks is exploited to identify the important features in latent representation. In particular, the proposed HRL is designed to treat each goal of a dialogue with the corresponding sub-policy so as to provide efficient dialogue policy learning by utilizing the guidance from human through action pruning and action evaluation, as well as the reward obtained from the interaction with the simulated user in the environment. Experimental results on ConvLab-2 framework show that the proposed method achieves state-of-the-art performance in dialogue policy optimization and outperforms the GPT-2 based solutions in end-to-end system evaluation.

Animality in Contemporary Italian Philosophy

Animality in Contemporary Italian Philosophy

Demonstrating CAT

Databases for OLTP are often the backbone for applications such as hotel room or cinema ticket booking applications. However, developing a conversational agent (i.e., a chatbot-like interface) to allow end-users to interact with an application using natural language requires both immense amounts of training data and NLP expertise. This motivates CAT , which can be used to easily create conversational agents for transactional databases. The main idea is that, for a given OLTP database, CAT uses weak supervision to synthesize the required training data to train a state-of-the-art conversational agent, allowing users to interact with the OLTP database. Furthermore, CAT provides an out-of-the-box integration of the resulting agent with the database. As a major difference to existing conversational agents, agents synthesized by CAT are data-aware. This means that the agent decides which information should be requested from the user based on the current data distributions in the database, which typically results in markedly more efficient dialogues compared with non-data-aware agents. We publish the code for CAT as open source.

Efficient Dialog Policy Learning by Reasoning with Contextual Knowledge

Goal-oriented dialog policy learning algorithms aim to learn a dialog policy for selecting language actions based on the current dialog state. Deep reinforcement learning methods have been used for dialog policy learning. This work is motivated by the observation that, although dialog is a domain with rich contextual knowledge, reinforcement learning methods are ill-equipped to incorporate such knowledge into the dialog policy learning process. In this paper, we develop a deep reinforcement learning framework for goal-oriented dialog policy learning that learns user preferences from user goal data, while leveraging commonsense knowledge from people. The developed framework has been evaluated using a realistic dialog simulation platform. Compared with baselines from the literature and the ablations of our approach, we see significant improvements in learning efficiency and the quality of the computed action policies.

Exomologesis as an absolute form of standing in inter-religious dialogue

The present study intends to offer another perspective over the inter-religious dialogue emphasising the spiritual state of exomologesis as an essential means of accomplishing a better and real understanding of a participant in dialogue. It makes some short analysis of penitential confession as homologation with the Logos, of the prayer as inner dialogue or confession or exomologesis with the Logos and of the confessions as a literary style, which all engages the deep, spiritual dimensions of communion with the Logos and finally analyses and exemplifies the ecstatic and existential spiritual dimensions of the exomologesis as an absolute form of standing in dialogue.Contribution: The study offers the necessary spiritual understanding and impulse for a more efficient inter-confessional and inter-religious dialogue, promoting HTS Journal as a herald of this dialogue essential and indispensable for the life of the world.

Engaging Religious Institutions and Faith-Based Communities in Public Health Initiatives: A Case Study of the Romanian Orthodox Church During the COVID-19 Pandemic.

The success of public health interventions is highly dependent on the compliance of the general population. State authorities often implement policies without consulting representatives of faith-based communities, thereby overlooking potential implications of public health measures for these parts of society. Although ubiquitous, these challenges are more readily observable in highly religious states. Romania serves as an illustrative example for this, as recent data identify it as the most religious country in Europe. In this paper, we discuss the contributions of the Romanian Orthodox Church (ROC), the major religious institution in the country, to the national COVID-19 mitigation efforts. We present not only the positive outcomes of productive consultations between public health authorities and religious institutions but also the detrimental impact of unidirectional communication. Our work highlights that an efficient dialogue with faith-based communities can greatly enhance the results of public health interventions. As the outlined principles apply to a variety of contexts, the lessons learned from this case study can be generalized into a set of policy recommendations for the betterment of future public health initiatives worldwide.

Integrating a spoken dialogue system, nursing records, and activity data collection based on smartphones

Background and Objective: This study describes the integration of a spoken dialogue system and nursing records on an Android smartphone application intending to help nurses reduce documentation time and improve the overall experience of a healthcare setting. The application also incorporates with collecting personal sensor data and activity labels for activity recognition. Methods: We developed a joint model based on a bidirectional long-short term memory and conditional random fields (Bi-LSTM-CRF) to identify user intention and extract record details from user utterances. Then, we transformed unstructured data into record inputs on the smartphone application. Results: The joint model achieved the highest F1-score at 96.79%. Moreover, we conducted an experiment to demonstrate the proposed model’s capability and feasibility in recording in realistic settings. Our preliminary evaluation results indicate that when using the dialogue-based, we could increase the percentage of documentation speed to 58.13% compared to the traditional keyboard-based. Conclusions: Based on our findings, we highlight critical and promising future research directions regarding the design of the efficient spoken dialogue system and nursing records.

Efficient Dialog Policy Learning With Hindsight, User Modeling, and Adaptation

Efficient Dialog Policy Learning With Hindsight, User Modeling, and Adaptation