Natural Language Dialogue System Research Articles

Reinforcement Learning in Social Sciences: A Survey

Reinforcement Learning (RL) has become one of the most prominent topics in artificial intelligence research. It is widely used in various fields, such as recommendation systems, psychology, economics, and natural language dialogue systems. Finding the best path of action to maximize cumulative reward is the long-term strategy of RL. Undertaking research may yield suboptimal immediate results but optimal long-term consequences. Economists can address difficult behavioral problems with knowledge, especially those generated by deep learning algorithms. We provide the most recent advancements in RL methods in this study, along with their applications in gaming, finance, and economics. The survey's last section discusses RL's present problems and potential future developments. Such open problems as sample efficiency, safety, and interpretability are currently being sought after by researchers. Moreover, several ambitious prospective applications of RL in a wide variety of domains are discussed. This study gives a comprehensive review of the many methods and uses of RL in social science. This study's results will give researchers a standard against which to evaluate the utility and efficacy of frequently used RL. Guide future investigations across several domains.

Privacy Preservation of Large Language Models in the Metaverse Era: Research Frontiers, Categorical Comparisons, and Future Directions

ABSTRACTLarge language models (LLMs), with their billions to trillions of parameters, excel in natural language processing, machine translation, dialog systems, and text summarization. These capabilities are increasingly pivotal in the metaverse, where they can enhance virtual interactions and environments. However, their extensive use, particularly in the metaverse's immersive platforms, raises significant privacy concerns. This paper analyzes existing privacy issues in LLMs, vital for both traditional and metaverse applications, and examines protection techniques across the entire life cycle of these models, from training to user deployment. We delve into cryptography, embedding layer encoding, differential privacy and its variants, and adversarial networks, highlighting their relevance in the metaverse context. Specifically, we explore technologies like homomorphic encryption and secure multiparty computation, which are essential for metaverse security. Our discussion on Gaussian differential privacy, Renyi differential privacy, Edgeworth accounting, and the generation of adversarial samples and loss functions emphasizes their importance in the metaverse's dynamic and interactive environments. Lastly, the paper discusses the current research status and future challenges in the security of LLMs within and beyond the metaverse, emphasizing urgent problems and potential areas for exploration.

YouTube Scholar: Advancing Education with AI Assistance

In the contemporary landscape of online educa- tion, the proliferation of educational content on platforms like YouTube has opened new avenues for learners. However, the sheer volume of videos presents a challenge, requiring innovative solutions. This project takes a pioneering approach by developing a specialized AI assistant for educational YouTube lectures, lever- aging advanced language models such as Generative Pretrained Transformers (GPT). This project focuses on the development of an AI assistant tailored specifically for educational YouTube lectures and courses. The primary goal is to enhance the learning experience by leveraging the capabilities of GPT-based models to provide personalised and contextually relevant interactions for learners. By harnessing the power of natural language understanding, generation, and dialog systems, the AI assistant aims to assist learners in navigating, understanding, and engaging with educa- tional content more effectively. The ultimate goal is to bridge the gap between the abundance of online educational content and learners’ comprehension, thereby revolutionizing the educational landscape in the digital age. By providing a sophisticated AI-driven companion, this project aspires to empower learners, making the educational journey more accessible, engaging, and conducive to deeper learning experiences. Through the integration of cutting-edge technologies, it envisions a future where learners can unlock the full potential of online education with confidence and ease

MedChatZH: A tuning LLM for traditional Chinese medicine consultations

Generative Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, including Question-Answering (QA) and dialogue systems. However, most models are trained on English data and lack strong generalization in providing answers in Chinese. This limitation is especially evident in specialized domains like traditional Chinese medical QA, where performance suffers due to the absence of fine-tuning and high-quality datasets. To address this, we introduce MedChatZH, a dialogue model optimized for Chinese medical QA based on transformer decoder with LLaMA architecture. Continued pre-training on a curated corpus of Chinese medical books is followed by fine-tuning with a carefully selected medical instruction dataset, resulting in MedChatZH outperforming several Chinese dialogue baselines on a real-world medical dialogue dataset. Our model, code, and dataset are publicly available on GitHub (https://github.com/tyang816/MedChatZH) to encourage further research in traditional Chinese medicine and LLMs.

Ontology-driven development of dialogue systems

A new technique and its software implementation are presented to create a deeply semantically structured ontology using plain natural language text as input, without regular structure or any previous tagging and markup. The new approach is primarily aimed at highly inflectional languages, and is implemented for Ukrainian. The automatically created ontologies (in OWL) could be easily converted to other graph databases formats, such as Neo4j, and were successfully evaluated as valid ontologies using Protégé, RDFlib and Neo4j environments. An integrated approach is proposed for the development of natural language dialogue systems driven by the ontologyrelated graph database using the Cypher language for the formal queries. The original phrases are subject to a special method of semantic analysis, which determines the type of formal query to the database. The essence of the analysis is that the text of the user’s phrase goes through a series of checks. Based on their results, a set of basic templates for the formal requests are determined, as well as additional constructions that are attached to the basic template. Some of the checks may also return the notion of substitution to certain specified positions of the formal query. Formal queries can return both contexts and lists of ontology concepts. In addition to concepts, queries can also return information about specific semantic predicates that connect them, which simplifies the synthesis of natural language responses. The synthesis of answers is based on special templates, the choice of which is directly related to the corresponding template of the formal query.

A dialogue system based on ontology automatically built through a natural language text analysis

An integrated approach is created to the development of natural-language dialogue systems driven by an ontological graph database. Ontology here has a defined regular structure that contains typed semantic relationships between concepts, as well as related contexts, which may also have a multilevel structure and additional typing. The ontology is created automatically due to the semantic analysis of a natural language using a specially developed original software, which is set up to work with inflected languages, in particular Ukrainian. The ontology description is serialized in OWL format. To work as part of the dialog system, the ontology is transferred to the graph database Neo4j. The Cypher language is used for formal queries. The original phrases of the user are subject to a special method of semantic analysis, which determines the type of formal query to the database. The essence of the analysis is that the text of the user phrase goes through a series of checks. Based on their results, a set of basic templates for formal requests is determined, as well as additional constructions that are attached to the basic template. Some of the checks may also return the notion of substitution to certain specified positions of the formal query. Formal queries can return both contexts and lists of ontology concepts. In addition to concepts, queries can also return information about specific semantic predicates that connect them, which simplifies the synthesis of natural language responses. The synthesis of answers is based on special templates, the choice of which is directly related to the corresponding template of the formal query.

Development of Natural Language Dialogue Software Systems

This paper discusses problems of natural language dialogue systems development. Here are considered different types of such program systems and their peculiarities based on our development experience. The systems discussed here are aimed at using graph ontological databases. Five basic types of natural language systems are highlighted: reference system, reference system with clarifying and technical questions, questionnaire system, active initiative system, control system. The first four of them are considered in detail. The reference system type, which is the basic type, is shown and discussed. Problems considered here are: natural language phrase to a formal query transformation, semantic analysis and answer formation. The ways are shown for these processes program implementation. For all the types the problem of the current dialogue subject keeping is considered, especially for an active initiative system where it is the most crucial. The different approaches are shown and compared for the principles of graph database (ontology) construction, which could be used in the dialogue systems.

Deep reinforcement learning: a survey

Deep reinforcement learning (RL) has become one of the most popular topics in artificial intelligence research. It has been widely used in various fields, such as end-to-end control, robotic control, recommendation systems, and natural language dialogue systems. In this survey, we systematically categorize the deep RL algorithms and applications, and provide a detailed review over existing deep RL algorithms by dividing them into modelbased methods, model-free methods, and advanced RL methods. We thoroughly analyze the advances including exploration, inverse RL, and transfer RL. Finally, we outline the current representative applications, and analyze four open problems for future research.

Designing a virtual patient dialogue system based on terminology-rich resources: Challenges and evaluation

AbstractVirtual patient software allows health professionals to practise their skills by interacting with tools simulating clinical scenarios. A natural language dialogue system can provide natural interaction for medical history-taking. However, the large number of concepts and terms in the medical domain makes the creation of such a system a demanding task. We designed a dialogue system that stands out from current research by its ability to handle a wide variety of medical specialties and clinical cases. To address the task, we designed a patient record model, a knowledge model for the task and a termino-ontological model that hosts structured thesauri with linguistic, terminological and ontological knowledge. We used a frame- and rule-based approach and terminology-rich resources to handle the medical dialogue. This work focuses on the termino-ontological model, the challenges involved and how the system manages resources for the French language. We adopted a comprehensive approach to collect terms and ontological knowledge, and dictionaries of affixes, synonyms and derivational variants. Resources include domain lists containing over 161,000 terms, and dictionaries with over 959,000 word/concept entries. We assessed our approach by having 71 participants (39 medical doctors and 32 non-medical evaluators) interact with the system and use 35 cases from 18 specialities. We conducted a quantitative evaluation of all components by analysing interaction logs (11,834 turns). Natural language understanding achieved an F-measure of 95.8%. Dialogue management provided on average 74.3 (±9.5)% of correct answers. We performed a qualitative evaluation by collecting 171 five-point Likert scale questionnaires. All evaluated aspects obtained mean scores above the Likert mid-scale point. We analysed the vocabulary coverage with regard to unseen cases: the system covered 97.8% of their terms. Evaluations showed that the system achieved high vocabulary coverage on unseen cases and was assessed as relevant for the task.

Natural language dialog system considering speaker’s emotion for open-ended conversation

To respond appropriately to an utterance, human-like communication system, should consider not only words in the utterance but also the speaker’s emotion. We thus proposed a natural language dialog system that can estimate the user’s emotion from utterances and respond on the basis of the estimated emotion. To estimate a speaker’s emotion (positive, negative, or neutral), 384 acoustic features extracted from an utterance are utilized by a Support Vector Machine (SVM). Artificial Intelligence Markup Language (AIML)-based response generating rules are expanded so that the speaker’s emotion can be considered as a condition of these rules. Two experiments were carried out to compare impressions of a dialog agent that considered emotion (proposed system) with those of an agent that did not (previous system). In the first experiment, 10 subjects evaluated the impressions after watch four conversation videos (no emotion estimation, correct emotion estimation, inadequate emotion estimation, and imperfect emotion estimation). In the second experiment, another 10 subjects evaluated the impressions after talk with both dialog agents. These experimental results and a demonstration of the proposed system will be shown in the presentation.

Usefulness, localizability, humanness, and language-benefit: additional evaluation criteria for natural language dialogue systems

Human---computer dialogue systems interact with human users using natural language. We used the ALICE/AIML chatbot architecture as a platform to develop a range of chatbots covering different languages, genres, text-types, and user-groups, to illustrate qualitative aspects of natural dialogue system evaluation. We present some of the different evaluation techniques used in natural dialogue systems, including black box and glass box, comparative, quantitative, and qualitative evaluation. Four aspects of NLP dialogue system evaluation are often overlooked: usefulness in terms of a user's qualitative needs, localizability to new genres and languages, humanness or naturalness compared to human---human dialogues, and language benefit compared to alternative interfaces. We illustrated these aspects with respect to our work on machine-learnt chatbot dialogue systems; we believe these aspects are worthwhile in impressing potential new users and customers.

Initial Implementation of Natural Language Turn-Based Dialog System

Our prototype implements a natural language dialog system for Excel spreadsheets. The work is motivated by a pilot study which shows that novice users have difficulties with the formula language of Excel and need interactive assistance. JustLingo1 allows spreadsheet calculations in ordinary, written English. Furthermore, users can extend the system functionality by explaining of the calculations to the prototype. The keyword-based system analyzes the input using natural language processing techniques and translates it into Excel formulas. It asks for missing information such as operands and target cells and provides alternatives if there are ambiguities. It also handles references to previous inputs, allowing step-by-step construction of calculations. An evaluation shows that it properly resolves 82% of references and correctly interprets 79,5% of overall user input. Although far from perfect, the prototype demonstrates that computers may soon begin to take on simple, limited-domain programming tasks based on natural-language input.1http://ps.ipd.kit.edu/english/JustLingo.php

New feature weighting approaches for speech-act classification

Speech-act classification is essential to generation and understanding of utterances within a natural language dialogue system since the speech-act of an utterance is closely tied to a user intention. The binary feature weighting scheme has mainly been used for speech-act classification because traditional feature weighting schemes such as tf.idf are not effective in speech-act classification due to the short length of utterances. This paper studies two effective feature weighting schemes using the category distributions of features: (1) the first one exploits the entropy of whole category distributions and (2) the second one the log-odds ratio of positive and negative category distributions. As a result, the proposed schemes show significant improvement on SVM and k-NN classifiers in our experiments.

A Natural Language Dialogue System for Impression-based Music Retrieval

Abstract —Impression-based music retrieval is the best way tofind pieces of music that suit the preferences, senses, or mentalstates of users. A natural language interface (NLI) is more usefuland effective than a graphical user interface for impression-basedmusic retrieval since an NLI interprets users’ spontaneous inputsentences to represent musical impressions and generates queryvectors for music retrieval. Existing impression-based musicretrieval systems, however, have no dialogue capabilities formodifying the most recently used query vector. We evaluateda natural language dialogue system we developed that deals notonly with 164 impression words but also with 14 comparativeexpressions, such as “a little more” and “more and more,” and,if necessary, modifies the most recently used query vector througha dialogue. We also evaluated performance using 35 participantsto determine the effectiveness of our dialogue system. Index Terms —Music retrieval, impression-based, naturallangauge dialogue.

Does textual feedback hinder spoken interaction in natural language?

The aim of the study was to determine the influence of textual feedback on the content and outcome of spoken interaction with a natural language dialogue system. More specifically, the assumption that textual feedback could disrupt spoken interaction was tested in a human–computer dialogue situation. In total, 48 adult participants, familiar with the system, had to find restaurants based on simple or difficult scenarios using a real natural language service system in a speech-only (phone), speech plus textual dialogue history (multimodal) or text-only (web) modality. The linguistic contents of the dialogues differed as a function of modality, but were similar whether the textual feedback was included in the spoken condition or not. These results add to burgeoning research efforts on multimodal feedback, in suggesting that textual feedback may have little or no detrimental effect on information searching with a real system. Statement of Relevance: The results suggest that adding textual feedback to interfaces for human–computer dialogue could enhance spoken interaction rather than create interference. The literature currently suggests that adding textual feedback to tasks that depend on the visual sense benefits human–computer interaction. The addition of textual output when the spoken modality is heavily taxed by the task was investigated.

Interactive tool for semi-automatic generation of a natural language grammar from a device descriptor

A method, system, and tool product for creating a grammar for a natural language dialog system from a device description is provided. The system can include a device descriptor for identifying configuration, interface, object, and attribute information of the device, a speech grammar for identifying one or more rules generated from the device descriptor that are supported by the device, a speech recognition system for invoking rules of the speech grammar, and a processor for facilitating interoperability and development of distributed applications and providing delineated coverage of the one or more rules in view of the device descriptor.

Effect of modality on collaboration with a dialogue system

The aim of this study was to investigate the influence of modality on collaboration processes between human and computer. Spoken and written interactions with a natural language dialogue system were compared using two real information-retrieval systems. In order to look for a restaurant (Experiment 1) or plan a trip (Experiment 2), participants performed several task-oriented dialogue scenarios. Although the spoken interaction mode was less efficient, it promoted collaboration, the use of personal pronouns and the literal form of the system's command utterances. Overall, in the written mode, the emphasis was on the task and its performance, rather than on dialogue. These findings are discussed with respect to the effect of communication mode on collaboration in human–computer dialogue.

Efficient Realization of Coordinate Structures in Combinatory Categorial Grammar

We describe a chart realization algorithm for Combinatory Categorial Grammar (CCG), and show how it can be used to efficiently realize a wide range of coordination phenomena, including argument cluster coordination and gapping. The algorithm incorporates three novel methods for improving the efficiency of chart realization: (i) using rules to chunk the input logical form into sub-problems to be solved independently prior to further combination; (ii) pruning edges from the chart based on the n-gram score of the edge’s string, in comparison to other edges with equivalent categories; and (iii) formulating the search as a best-first anytime algorithm, using n-gram scores to sort the edges on the agenda. The algorithm has been implemented as an extension to the OpenCCG open source CCG parser, and initial performance tests indicate that the realizer is fast enough for practical use in natural language dialogue systems.

Towards efficient human machine speech communication

This research investigates the design and performance of the Speech Graffiti interface for spoken interaction with simple machines. Speech Graffiti is a standardized interface designed to address issues inherent in the current state-of-the-art in spoken dialog systems such as high word-error rates and the difficulty of developing natural language systems. This article describes the general characteristics of Speech Graffiti, provides examples of its use, and describes other aspects of the system such as the development toolkit. We also present results from a user study comparing Speech Graffiti with a natural language dialog system. These results show that users rated Speech Graffiti significantly better in several assessment categories. Participants completed approximately the same number of tasks with both systems, and although Speech Graffiti users often took more turns to complete tasks than natural language interface users, they completed tasks in slightly less time.

Mode and modal transfer effects on performance and discourse organization with an information retrieval dialogue system in natural language

This paper describes an experiment on the effects of learning, mode of interaction (written vs. spoken) and transfer mode on user performance and discourse organization during interaction with a natural language dialogue system. Forty-eight participants took part in a series of 12 dialogues with an information retrieval system presented either in the written or the spoken mode during the first six dialogues. The next six dialogues were then presented either in the same interaction mode or in another mode. The analysis of the results showed that performance (time, number of effective turns) improved throughout the dialogues whatever the mode of interaction. Nevertheless, performance was higher in the written mode. Moreover, mode-specific characteristics were observed. These consisted in greater use of subject pronouns and articles in the spoken mode. Similarly, in the spoken mode, the users found it easier to re-use the formulations presented in the system speech than in the written mode. Furthermore, the analysis also revealed a positive transfer effect on performance and discourse organization when the individuals first interacted in the spoken mode and then in the written mode. Both positive and negative transfer effects were observed when the individuals interacted first in the written mode followed by the spoken mode. The implications of the results are discussed in terms of direct and indirect consequences of modality effects on natural language dialogue interaction.