Explore the vast range of titles available.

Dialogue policy learning (DPL) is a key component in a task-oriented dialogue (TOD) system. Its goal is to decide the next action of the dialogue system, given the dialogue state at each turn based on a learned dialogue policy. Reinforcement learning (RL) is widely used to optimize this dialogue policy. In the learning process, the user is regarded as the environment and the system as the agent. In this paper, we present an overview of the recent advances and challenges in dialogue policy from the perspective of RL. More specifically, we identify the problems and summarize corresponding solutions for RL-based dialogue policy learning. In addition, we provide a comprehensive survey of applying RL to DPL by categorizing recent methods into five basic elements in RL. We believe this survey can shed light on future research in DPL.

Successful applications of deep learning technologies in the natural language processing domain have improved text-based intent classifications. However, in practical spoken dialogue applications, the users’ articulation styles and background noises cause automatic speech recognition (ASR) errors, and these may lead language models to misclassify users’ intents. To overcome the limited performance of the intent classification task in the spoken dialogue system, we propose a novel approach that jointly uses both recognized text obtained by the ASR model and a given labeled text. In the evaluation phase, only the fine-tuned recognized language model (RLM) is used. The experimental results show that the proposed scheme is effective at classifying intents in the spoken dialogue system containing ASR errors.

The rapid advancement of Large Language Models (LLMs) has led to substantial investment in enhancing their capabilities and expanding their feature sets. Despite these developments, a critical gap remains between model sophistication and their dependable deployment in real-world applications. A key concern is the inconsistency of LLM-generated outputs in production environments, which hinders scalability and reliability. In response to these challenges, we propose a novel framework that integrates custom-defined, rule-based logic to constrain and guide LLM behavior effectively. This framework enforces deterministic response boundaries while considering the model’s reasoning capabilities. Furthermore, we introduce a quantitative performance scoring mechanism that achieves an 85.5% improvement in response consistency, facilitating more predictable and accountable model outputs. The proposed system is industry-agnostic and can be generalized to any domain with a well-defined validation schema. This work contributes to the growing research on aligning LLMs with structured, operational constraints to ensure safe, robust, and scalable deployment.

Speaking in a foreign language is considered challenging to both teach and learn. Virtual humans (VHs), as conversational agents (CAs), provide opportunities to practise speaking skills. Lower secondary school students (N = 25) engaged in an AI-based spoken dialogue system (SDS) and interacted verbally with VHs in simulated everyday-life scenarios to solve given tasks. Our analysis is based on system-generated metrics and self-reported experiences collected through questionnaires, logbooks, and interviews. Thematic analysis resulted in seven themes, revolving around the speaking practice method, scenarios and technology, which, in combination with descriptive statistics, enabled a deeper understanding of the students' experiences. The results indicate that, on average, they found it easy, fun, and safe, but sometimes frustrating in scenarios not always relevant to their everyday lives. Factors suggested as underlying the levels of experienced frustration include technical issues and constraints with the system, such as not being understood or heard as expected. The findings suggest that lower secondary school students conversing with VHs in the SDS in an institutional educational context facilitated a beneficial opportunity for practising speaking skills, especially pronunciation and interaction in dialogues, aligning with the key principles of second language acquisition (SLA) for language development.

Since understanding a user’s request has become a critical task for the artificial intelligence speakers, capturing intents and finding correct slots along with corresponding slot value is significant. Despite various studies concentrating on a real-life situation, dialogue system that is adaptive to in-vehicle services are limited. Moreover, the Korean dialogue system specialized in an vehicle domain rarely exists. We propose a dialogue system that captures proper intent and activated slots for Korean in-vehicle services in a multi-tasking manner. We implement our model with a pre-trained language model, and it includes an intent classifier, slot classifier, slot value predictor, and value-refiner. We conduct the experiments on the Korean in-vehicle services dataset and show 90.74% of joint goal accuracy. Also, we analyze the efficacy of each component of our model and inspect the prediction results with qualitative analysis.

A conversational chatbot or dialogue system is a computer program designed to simulate conversation with human users, especially over the Internet. These chatbots can be integrated into messaging apps, mobile apps, or websites, and are designed to engage in natural language conversations with users. There are also many applications in which chatbots are used for educational support to improve students’ performance during the learning cycle. The recent success of ChatGPT also encourages researchers to explore more possibilities in the field of chatbot applications. One of the main benefits of conversational chatbots is their ability to provide an instant and automated response, which can be leveraged in many application areas. Chatbots can handle a wide range of inquiries and tasks, such as answering frequently asked questions, booking appointments, or making recommendations. Modern conversational chatbots use artificial intelligence (AI) techniques, such as natural language processing (NLP) and artificial neural networks, to understand and respond to users’ input. In this study, we will explore the objectives of why chatbot systems were built and what key methodologies and datasets were leveraged to build a chatbot. Finally, the achievement of the objectives will be discussed, as well as the associated challenges and future chatbot development trends.

Chatbots are intelligent conversational computer systems designed to mimic human conversation to enable automated online guidance and support. The increased benefits of chatbots led to their wide adoption by many industries in order to provide virtual assistance to customers. Chatbots utilise methods and algorithms from two Artificial Intelligence domains: Natural Language Processing and Machine Learning. However, there are many challenges and limitations in their application. In this survey we review recent advances on chatbots, where Artificial Intelligence and Natural Language processing are used. We highlight the main challenges and limitations of current work and make recommendations for future research investigation.

Recently, interaction between humans and dialog systems has become increasingly common and sophisticated. Humans establish good relationships with others using various linguistic considerations (e.g., politeness and speech level) in dialog. However, the effect of linguistic considerations used by dialog systems has remained unclear. This study examines the effects of the speech level shift used by a text chat dialog system in Japanese-language user dialog. We designed a rule-based, non-task-oriented text dialog system that controls formal and informal speech levels for Japanese dialog; the effects of a shift in the speech level used by the dialog system were verified through psychological experiments using text chats (n = 134). The speech level control method was constructed with reference to statistical information from the BTSJ Japanese natural conversation corpus and knowledge of linguistic considerations (politeness). The results of the experiment showed that 41.3% of the participants who interacted with the dialog system that shifted the speech level also shifted their speech levels in response. Moreover, a subjective evaluation revealed that participants who noticed the speech level shift of the dialog system felt that this system paid attention to its relationship with the participants. The experimental results suggest that a dialog system can realize dialog in which the user and system both adjust their relationship through dynamic speech level shifts. This study identifies the importance of dynamic speech level shifts, an important factor for expressing politeness, in interactions between humans and dialog systems.

In recent years, researchers from the fields of computer vision, language, graphics, and robotics have tackled Embodied AI research. Embodied AI can learn through interaction with the real world and virtual environments and can perform various tasks in virtual environments using virtual robots. However, many of these are one-way tasks in which the interaction is interrupted only by answering questions or requests to the user. In this research, we aim to develop a two-way interactive navigation system by introducing knowledge-based reasoning to Embodied AI research. Specifically, the system obtains guidance candidates that are difficult to identify with existing common-sense reasoning alone by reasoning with the constructed home ontology. Then, we develop a two-way interactive navigation system in which the virtual robot can guide the user to the location in the virtual home environment that the user needs while repeating multiple conversations with the user. We evaluated whether the proposed system was able to present appropriate guidance locations as candidates based on users’ speech input about their home environment. For the evaluation, we extracted the speech data from the corpus of daily conversation, the speech data created by the subject, and the correct answer data for each data and calculated the precision, recall, and F-value. As a result, the F-value was 0.47 for the evaluation data extracted from the daily conversation corpus, and the F-value was 0.49 for the evaluation data created by the subject.

In this paper, we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation, in and of itself, is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost- and time-intensive. Thus, much work has been put into finding methods which allow a reduction in involvement of human labour. In this survey, we present the main concepts and methods. For this, we differentiate between the various classes of dialogue systems (task-oriented, conversational, and question-answering dialogue systems). We cover each class by introducing the main technologies developed for the dialogue systems and then present the evaluation methods regarding that class.