Dialogue Response Research Articles

Pengembangan Aplikasi Chatbot Telegram Menggunakan Framework Rasa untuk Pelayanan Administrasi di Perguruan Tinggi Universitas Stikubank

The administrative services in universities are currently still conventional, resulting in many difficulties due to the mismatched time. For this research, a Telegram chatbot application will be developed to provide various answers to administrative inquiries in universities automatically. The chatbot application will be developed using the Rasa Open Source framework. This research collects data from several frequently asked questions by students and prospective students to the Biro Administrasi Akademik dan Kemahasiswaan (BAAK) as the initial data for the chatbot application. From this data, it will be transformed into Natural Language Understanding (NLU) and dialogue data. The number of NLU sentence examples is 213, and there are 27 dialogue examples. As a result, the chatbot application can understand user inquiries well, but it experiences some errors in generating dialogue responses.

Humanising Online Pedagogy through Asynchronous Discussion Forums

Humanising pedagogy has been a focus of recent research as more universities move to online and blended models of instruction. Online learning has been linked to feelings of isolation, disconnection, and depersonalisation of the learning experience for many students. In South Africa, the shift to online instruction took place in the context of the Covid-19 pandemic and recent student movements that brought attention to how the country’s violent history resulted in structural inequalities in terms of race and class that affect learning environments. Thus, humanising pedagogy also meant recognising and addressing how students’ contextual challenges might affect their feelings of connection in the learning environment. In this article, we present a case study of a first-year course at a South African university where we used online discussion forums that required students to engage with weekly forum tasks. Through thematic content analysis of students’ dialogic responses on these forum tasks, we demonstrate how the tasks facilitated humanising pedagogy by allowing students to use their authentic voices, to form social connections, and to reflect their affective and personal experiences. We argue that interactive, asynchronous online forums can be effective tools to facilitate humanising online pedagogy when these forums are designed in ways that encourage dialogic learning, use content that is relevant to students’ contexts, and give students agency by allowing them to select texts for discussion and share their diverse perspectives. Our analysis also showed limitations to forum discussions which include students echoing responses and instances of silencing and unsupportive group dynamics.

The Meaning of Sacraments as “Signs of Faith” – Reciprocity between faith and sacraments

God, through the Church, enters into a personal dialogue with man out of his desire to save him. This dialogue is carried out in different ways and based on certain criteria. One of these is the sacramental reality. The sacraments are a concretization of the divine action that fully realizes the mystery of salvation. In 2020, a document of the International Theological Commission was published with the title: Reciprocity between faith and sacraments in the sacramental economy. Here it is reaffirmed that the essence of faith is found in the principle of sacramentality. This principle represents the very nature of Christian revelation, namely, the dialogical response of the believer and the Christian community, such that there is no authentic sacramental celebration without faith. The theological study has always linked the doctrine of the sacraments and their celebration to the gift of faith that the believer receives from God exclusively based on the merits of Jesus Christ. On the other hand, Christ, giving birth to the sacraments, also gives them the ontological power that works on the inner plane in the human being. This gives the believer a certain spiritual experience that enables him to live and act as a person of faith. It is therefore important to understand the relationship between faith and sacraments, starting from the meaning of the notion of faith

Dynamically retrieving knowledge via query generation for informative dialogue generation

Knowledge-driven dialogue systems have recently made remarkable breakthroughs. Compared with general dialogue systems, superior knowledge-driven dialogue systems can generate more informative and knowledgeable responses with pre-provided knowledge. However, in practical applications, the knowledge-driven dialogue systems cannot be supplied with relevant knowledge beforehand. Hence, to enhance the practicality of the knowledge-driven dialogue systems, it is crucial to devise a method to dynamically retrieve pertinent knowledge based on the context. In addressing this challenge, we introduce a knowledge-driven dialogue system called DRKQG (Dynamically Retrieving Knowledge via Query Generation for informative dialogue response). Specifically, this system is composed of two main modules: a query generation module and a response generation module. Initially, a time-aware mechanism is employed to capture contextual information, enabling the generation of a query for knowledge retrieval through a search engine. Subsequently, we incorporate the copy mechanism and transformers, empowering the response generation module to create responses based on both the context and retrieved knowledge. Experimental results at LIC2022, Language and Intelligence Technology Competition, show that our module outperforms the baseline model by a large margin on automatic evaluation metrics, while human evaluation by the Baidu Linguistics team shows that our system achieves impressive results in Factually Correct and Knowledgeable.

‘Slow togethering’ as a tool for dialogic development amongst dance dramaturgs

Thisarticle is an experiment in ‘slow togethering’ between two dance dramaturgs. Itinvestigates dance dramaturgy practice beyond the making of a creative product,in which dialogue aboutpracticeoccurs simultaneously with dialogue aspractice.Thus, the authors propose this article itself as practice research.Weunderstand ‘slow togethering’ as a form of dialogue over time: the articlepresents a series of exchanges by the authors which were written over a periodof one month. Alongside, there is a commentary reflecting on these texts andthe overall process.Withthis format, the authors aim to disrupt the conventions of linear andsequential thinking, offering an opportunity for the reader to exploredifferent ways of encountering the narratives of the article.In this vein,the authors suggest the reader as a dialogue partner in their own right,acknowledging that a reader’s dialogic response resides in a space and timebeyond that of the article.

Christian Responses to Psilocybin-Assisted Therapy and Potential Religious and Spiritual Experiences

This paper explores Christian responses to religious and spiritual experiences (RSEs) associated with psilocybin-assisted therapy (PAT). It addresses the challenges of defining and understanding spiritual and religious experiences and examines the theological implications of PAT-induced RSEs. It highlights the growing acceptance of PAT as a therapeutic approach and its potential benefits for mental health. It also discusses the occurrence of RSEs in individuals undergoing such therapy. In response to these experiences, I propose four possible Christian perspectives: viewing RSEs as illusions, perceiving them as inherently evil, considering them as encounters with the Christian God, or acknowledging their reality while recognizing their broader occurrence beyond the Christian tradition. The paper emphasizes the importance of active dialog and collective responses within the Christian community to avoid hindering individuals seeking mental health relief through PAT. By engaging with these theological questions, Christians can navigate the complexities and potential benefits of RSEs in the context of psychedelic-assisted therapy.

“Reading is Social”: Dialogic Responses to Interactive Read-Alouds with Nonfiction Picturebooks

“Reading is Social”: Dialogic Responses to Interactive Read-Alouds with Nonfiction Picturebooks

Dialog generation model based on variational Bayesian knowledge retrieval method

For dialog generation models that introduce external knowledge, the key challenge lies in how to select the relevant knowledge. The existing common method is to directly use a retriever to fetch knowledge according to the prior distribution that is only conditioned on dialog history. In fact, the response also contains crucial information that is helpful for knowledge retrieval. If we can make use of it and conduct posterior retrieval of relevant knowledge according to both dialog history and response, the selected knowledge will be more relevant to the dialog. Therefore, this paper proposes a dialog generation model (DG-VBKR) based on variational Bayesian knowledge retrieval method, which consists of two modules: knowledge retrieval and dialog generation. During the training process, both a prior knowledge retriever and a posterior knowledge retriever are trained simultaneously, and the prior knowledge retriever is guided by the posterior knowledge retriever. Specifically, the KL Divergence is used to measure the difference between the retrieval results of the two retrievers and make the trained prior knowledge retriever achieve a similar effect to the posterior knowledge retriever. In addition, this paper constructs four versions of the proposed model by using GPT-2, BART, TransformerDecoder, and TransformerEnc−Dec in dialog generation module. The experimental results show that the DG-VBKR model achieves certain improvements on several metrics compared to the baseline models. Among them, the GPT-2 version model with the best performance has improved by 7.0% on the PPL metric compared with the model using only prior knowledge retrieval. This indicates that the DG-VBKR model can effectively select knowledge related to the dialog to generate high-quality responses.

Multi-modal multi-hop interaction network for dialogue response generation

Multi-modal multi-hop interaction network for dialogue response generation

ConvNTM: Conversational Neural Topic Model

Topic models have been thoroughly investigated for multiple years due to their great potential in analyzing and understanding texts. Recently, researchers combine the study of topic models with deep learning techniques, known as Neural Topic Models (NTMs). However, existing NTMs are mainly tested based on general document modeling without considering different textual analysis scenarios. We assume that there are different characteristics to model topics in different textual analysis tasks. In this paper, we propose a Conversational Neural Topic Model (ConvNTM) designed in particular for the conversational scenario. Unlike the general document topic modeling, a conversation session lasts for multiple turns: each short-text utterance complies with a single topic distribution and these topic distributions are dependent across turns. Moreover, there are roles in conversations, a.k.a., speakers and addressees. Topic distributions are partially determined by such roles in conversations. We take these factors into account to model topics in conversations via the multi-turn and multi-role formulation. We also leverage the word co-occurrence relationship as a new training objective to further improve topic quality. Comprehensive experimental results based on the benchmark datasets demonstrate that our proposed ConvNTM achieves the best performance both in topic modeling and in typical downstream tasks within conversational research (i.e., dialogue act classification and dialogue response generation).

Automated speech scoring of dialogue response by Japanese learners of English as a foreign language

ABSTRACT Purpose: This study builds a new system for automatically assessing learners’ speech elicited from an oral discourse completion task (DCT), and evaluates the prediction capability of the system with a view to better understanding factors deemed influential in predicting speaking proficiency scores and the pedagogical implications of the system. Methodology: We developed a system with a tripartite structure using an automatic speech recogniser, a set of modules that compute a number of speech features, and a scoring model. In total, 210 participants with intermediate English language proficiency level were administered a multi-turn oral DCT, a task which closely resembles discourse in real-life situations. The collected speech and transcribed files were eyeballed and rated by human raters first. Eighty percent of the original dataset was then used to train and examine our prediction model against the remainder of the dataset. Findings: The exact agreement between human and machine scores was 72%, moderately high, and comparable to the literature on automated speech scoring. It could provide a basis for deploying the system in a low-stakes practice environment. Originality/value: This study makes a unique contribution to the wider scholarship, where the use of single-turn DCTs remains prevalent, by presenting a new reliable scoring system for learner speech using an automated DCT with multiple turns. It offers useful insight into ways in which the system could be used in a low-stakes environment, including foreign language classroom settings.

Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery

Abstract In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDialog curated by ourselves. The current models indeed suffer from spurious correlations and have a tendency to generate irrelevant and generic responses. Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference using a conditional independence classifier. The classifier is trained by a constrained self-training method, coined ConSTrain, to overcome data sparsity. The experimental results based on both human and automatic evaluation show that our method significantly outperforms the competitive baselines in terms of relevance, informativeness, and fluency.

Towards Informative and Diverse Dialogue Systems Over Hierarchical Crowd Intelligence Knowledge Graph

Knowledge-enhanced dialogue systems aim at generating factually correct and coherent responses by reasoning over knowledge sources, which is a promising research trend. The truly harmonious human-agent dialogue systems need to conduct engaging conversations from three aspects as humans, namely (1) stating factual contents (e.g., records in Wikipedia), (2) conveying subjective and informative opinions about objects (e.g., user discussions on Twitter), and (3) impressing interlocutors with diverse expression styles (e.g., personalized expression habits). The existing knowledge base is a standardized and unified coding for factual knowledge, which could not portray the other two kinds of knowledge to make responses more informative and expressive diverse. To address this, we present CrowdDialog , a crowd intelligence knowledge-enhanced dialogue system, which takes advantage of “crowd intelligence knowledge” extracted from social media (with rich subjective descriptions and diversified expression styles) to promote the performance of dialogue systems. Firstly, to thoroughly mine and organize the crowd intelligence knowledge underlying large-scale and unstructured online contents, we elaborately design the C rowd I ntelligence K nowledge G raph ( CIKG ) structure, including the domain commonsense subgraph, descriptive subgraph, and expressive subgraph. Secondly, to reasonably integrate heterogeneous crowd intelligence knowledge into responses while ensuring logicality and fluency, we propose the G ated F usion with D ynamic Knowledge- D ependent ( GFDD ) model, which generates responses from the semantic and syntactic perspective with the context-aware knowledge gate and dynamic knowledge decoding. Finally, extensive experiments over both Chinese and English dialogue datasets demonstrate that our approach GFDD outperforms competitive baselines in terms of both automatic evaluation and human judgments. Besides, ablation studies indicate that the proposed CIKG has the potential to promote dialogue systems to generate fluent, informative, and diverse dialogue responses.

End-to-end dialogue structure parsing on multi-floor dialogue based on multi-task learning.

A multi-floor dialogue consists of multiple sets of dialogue participants, each conversing within their own floor. In the multi-floor dialogue, at least one multi-communicating member who is a participant of multiple floors and coordinates each to achieve a shared dialogue goal. The structure of such dialogues can be complex, involving intentional structure and relations that are within or across floors. In this study, We proposed a neural dialogue structure parser with an attention mechanism that applies multi-task learning to automatically identify the dialogue structure of multi-floor dialogues in a collaborative robot navigation domain. Furthermore, we propose to use dialogue response prediction as an auxiliary objective of the multi-floor dialogue structure parser to enhance the consistency of the multi-floor dialogue structure parsing. Our experimental results show that our proposed model improved the dialogue structure parsing performance more than conventional models in multi-floor dialogue.

Using a Google Web Search Analysis to Assess the Utility of ChatGPT in Total Joint Arthroplasty

BackgroundRapid technological advancements have laid the foundations for the use of artificial intelligence in medicine. The promise of machine learning (ML) lies in its potential ability to improve treatment decision making, predict adverse outcomes, and streamline the management of perioperative healthcare. In an increasing consumer-focused health care model, unprecedented access to information may extend to patients using ChatGPT to gain insight into medical questions. The main objective of our study was to replicate a patient’s internet search in order to assess the appropriateness of ChatGPT, a novel machine learning tool released in 2022 that provides dialogue responses to queries, in comparison to Google Web Search, the most widely used search engine in the United States today, as a resource for patients for online health information. For the 2 different search engines, we compared i) the most frequently asked questions (FAQs) associated with total knee arthroplasty (TKA) and total hip arthroplasty (THA) by question type and topic; ii) the answers to the most frequently asked questions; as well as iii) the FAQs yielding a numerical response. MethodsA Google web search was performed with the following search terms: “total knee replacement” and “total hip replacement.” These terms were individually entered and the first 10 FAQs were extracted along with the source of the associated website for each question. The following statements were inputted into ChatGPT: 1) “Perform a google search with the search term ‘total knee replacement’ and record the 10 most FAQs related to the search term” as well as 2) “Perform a google search with the search term ‘total hip replacement’ and record the 10 most FAQs related to the search term.” A Google web search was repeated with the same search terms to identify the first 10 FAQs that included a numerical response for both “total knee replacement” and “total hip replacement.” These questions were then inputted into ChatGPT and the questions and answers were recorded. ResultsThere were 5 of 20 (25%) questions that were similar when performing a Google web search and a search of ChatGPT for all search terms. Of the 20 questions asked for the Google Web Search, 13 of 20 were provided by commercial websites. For ChatGPT, 15 of 20 (75%) questions were answered by government websites, with the most frequent one being PubMed. In terms of numerical questions, 11 of 20 (55%) of the most FAQs provided different responses between a Google web search and ChatGPT. ConclusionA comparison of the FAQs by a Google web search with attempted replication by ChatGPT revealed heterogenous questions and responses for open and discrete questions. ChatGPT should remain a trending use as a potential resource to patients that needs further corroboration until its ability to provide credible information is verified and concordant with the goals of the physician and the patient alike.

Toward Explainable Dialogue System Using Two-stage Response Generation

In recent years, neural networks have achieved impressive performance on dialogue response generation. However, most of these models still suffer from some shortcomings, such as yielding uninformative responses and lacking explainable ability. This article proposes a Two-stage Dialogue Response Generation model (TSRG), which specifies a method to generate diverse and informative responses based on an interpretable procedure between stages. TSRG involves a two-stage framework that generates a candidate response first and then instantiates it as the final response. The positional information and a resident token are injected into the candidate response to stabilize the multi-stage framework, alleviating the shortcomings in the multi-stage framework. Additionally, TSRG allows adjusting and interpreting the interaction pattern between the two generation stages, making the generation response somewhat explainable and controllable. We evaluate the proposed model on three dialogue datasets that contain millions of single-turn message-response pairs between web users. The results show that, compared with the previous multi-stage dialogue generation models, TSRG can produce more diverse and informative responses and maintain fluency and relevance.

Search-engine-augmented dialogue response generation with cheaply supervised query production

Knowledge-aided dialogue response generation aims at augmenting chatbots with relevant external knowledge in the hope of generating more informative responses. The majority of previous work assumes that the relevant knowledge is given as input or retrieved from a static pool of knowledge. However, this assumption violates the real-world situation, where knowledge is continually updated and a chatbot has to dynamically retrieve useful knowledge. We propose a dialogue model that can access the vast and dynamic information from any search engine for response generation. As the core module, a query producer is used to generate queries from a dialogue context to interact with a search engine. We design a training algorithm using cheap noisy supervision for the query producer, where the signals are obtained by comparing retrieved articles with the next dialogue response. As the result, the query producer is adjusted without any human annotation of gold queries, making it easily transferable to other domains and search engines. Experiments show that our query producer can achieve R@1 and R@5 rates of 62.4% and 74.8% for retrieving gold knowledge, and the overall model generates better responses over strong knowledge-aided baselines using BART [1] and other typical systems.

Japanese complaint responses in textbook dialogues and ordinary conversations: learning objects to expand interactional repertoires

Abstract This study examines Japanese complaint responses appearing in naturally occurring interaction and textbook dialogues. The comparative analysis highlights that complaint responses in textbooks differ from those in mundane conversation. The inevitable difficulty for textbooks to reflect temporal and multimodal features of interaction results in the designs of affiliative responses being minimal and disaffiliative responses being more explicit. In contrast, conversation data indicates that complaint response turns are more intricately designed with multimodal semiotic resources and are precisely positioned according to the sequential development of complaints. By conducting empirical analyses, the study identifies interactional repertoires that are not observed in textbooks but employed in actual conversations. In doing so, it aims to expand the variety of the analysis of textbook dialogues to help calibrate the input for Japanese language pedagogy, while presenting a reference point for Japanese language learners to better understand the interactional organization of complaint sequences in mundane conversations.

OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue

AbstractThis paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: Dialogue state tracker (DST) and response generator (RG). The dialogue state consists of the domain-slot-value triples, which are regarded as the user’s constraints to search the domain-related databases. The large-scale task-oriented dialogue data with the annotated structured dialogue state usually are inaccessible. It prevents the development of the pretrained language model for the task-oriented dialogue. We propose a simple yet effective pretraining method to alleviate this problem, which consists of two pretraining phases. The first phase is to pretrain on large-scale contextual text data, where the structured information of the text is extracted by the information extracting tool. To bridge the gap between the pretraining method and downstream tasks, we design two pretraining tasks: ontology-like triple recovery and next-text generation, which simulates the DST and RG, respectively. The second phase is to fine-tune the pretrained model on the TOD data. The experimental results show that our proposed method achieves an exciting boost and obtains competitive performance even without any TOD data on CamRest676 and MultiWOZ benchmarks.

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.