Human-machine Dialogue Research Articles

Substantive and Emotional: The Anthropomorphic Evolution of Generative AITaking GPT-4o as an Example

Under the background of the rapid development of artificial intelligence technology, "personal publishing" represented by blog in the past has transformed into "human-computer co-creation", showing a new human-computer interaction relationship, and generative artificial intelligence has become the "collaborator" of human content creation. The flagship multimodal large language model "anthropomorphism" represented by GPT-4o is evolving from "linguistic anthropomorphism" to "emotional anthropomorphism". Based on the anthropomorphic theory, this paper aims to reveal that GPT-4o, while demonstrating its linguistic intelligence in the human-machine co-created dialogue, simulates human emotional response, showing empathy and "resonance", that is, the "anthropomorphic" process at the two levels of "words have things" and "words have feelings". It also reflects on the potential ethical challenges of the anthropomorphic evolution of generative AI to future human society.

Heterogeneous Views and Spatial Structure Enhancement for triple error detection

Knowledge graph error detection is to identify erroneous triples in knowledge graphs that are inconsistent with objective facts in the real world. In practice, the quality of knowledge graphs is an indispensable foundation for the widespread and accurate knowledge application services such as intelligent retrieval and human machine dialogue. Technically, the existing knowledge graph error detection methods face the following two problems: few available negative samples of triples, and an uneven data distribution. That distribution is caused by the large disparity in the number of head and tail entities belonging to the same relationship and the disparity in the number of triples with different relationships. To alleviate these problems, this paper proposes an approach based on the Heterogeneous Views and Spatial Structure Enhancement (HVSSE) in a contrastive learning framework for triple error detection task. Specifically, the heterogeneous views are constructed to include four kinds of triple views, i.e., positive and negative triple views based on head or tail entity co-occurrence. Moreover, Graph-Spatial-Transformer with an explicit spatial structure encoding is designed to fully capture the contextual information of triple nodes. Thereby, driven by the framework of contrastive learning, our HVSSE model can not only learn more discriminative embedding of triples, but also capture the local structure of triples and global contextual information of knowledge graphs. Experimental results on five public datasets indicate that our proposed approach is superior to the state-of-the-art methods, showing its the effectiveness on triple error detection.

Ultra-broad sensing range, high sensitivity textile pressure sensors with heterogeneous fibre architecture and molecular interconnection strategy

Textile-based pressure sensors have garnered extensive attentions owing to their potentials in health monitoring, human–machine interactions, wearable human–machine interfaces (HMIs) and soft robotics. High sensitivity over a broad sensing range are highly desired yet challenging for textile pressure sensors due to the incompressibility of matrix materials and the stiffening of microstructures. Herein, we developed a high performance pressure sensor based on the silk/3-Aminopropyltriethoxy-silane/titanium carbide (Silk/APTES/MXene) film. The silk is designed with heterogeneous fiber architecture, which enables rich and multi-level contact pattern and could compensate for the effect of structural stiffening. Furthermore, APTES molecules are used to enhance the interface bonding between MXene and silk, promoting the mechanical stability of the sensor. Benefiting from these advantages, the Silk/APTES/MXene sensor device is achieved with high sensitivity of 17.1 KPa−1 over an ultra-broad sensing range up to 3.3 MPa (R2 = 0.997), ultra-low detection limit (0.25 Pa), and low fatigue toughness after 5000 cycles loading and unloading. With these merits, we have demonstrated its capability for a series of human motion detection (such as foot movement detection, arm/wrist/finger bending, etc) and an overall accuracy of 95 % is obtained with the help of CNN-based convolution neural architecture. More significantly, we have built an entire intelligent human–machine dialogue system and a patient-audience dialogue system, from lip/sign language recognition to real-time screen display and final voice output.

Human-machine dialogues unveiled: an in-depth exploration of individual attitudes and adoption patterns toward AI-powered ChatGPT systems

PurposeChatGPT is an advanced artificial intelligence (AI) form that can generate human-like text based on large amounts of data. This paper aims to empirically examine the ChatGPT adoption level among Indian individuals by considering the key factors in determining individuals’ attitudes and intentions toward newly emerged AI tools.Design/methodology/approachThis paper used “partial least square structural equation modeling” (PLS-SEM) to investigate the relation among several latent factors by applying a representative sample of 351 individuals.FindingsThis study found that trialability, performance expectancy and personal innovativeness significantly influence individuals' attitudes, while compatibility and effort expectancy do not significantly impact attitudes. Additionally, trialability, performance expectancy, effort expectancy, personal innovativeness and attitude significantly influence behavioral intentions. However, compatibility has an insignificant impact on behavioral intention. Moreover, the research highlights that attitude and behavioral intention directly correlate with actual use. Specifically, the absence of compatibility makes people hesitate to use technology that does not meet their specific needs.Practical implicationsThese unique findings provide valuable insights for technology service providers and government entities. They can use this information to shape their policies, deliver timely and relevant updates and enhance their strategies to boost the adoption of ChatGPT.Originality/valueThis paper is one of the pioneering attempts to exhibit the research stream to understand the individual acceptance of ChatGPT in an emerging country. Moreover, it gained significant attention from individuals for delivering a unique experience and promising solutions.

Personality prediction from task-oriented and open-domain human–machine dialogues

If a dialogue system can predict the personality of a user from dialogue, it will enable the system to adapt to the user’s personality, leading to better task success and user satisfaction. In a recent study, personality prediction was performed using the Myers–Briggs Type Indicator (MBTI) personality traits with a task-oriented human–machine dialogue using an end-to-end (neural-based) system. However, it is still not clear whether such prediction is generally possible for other types of systems and user personality traits. To clarify this, we recruited 378 participants, asked them to fill out four personality questionnaires covering 25 personality traits, and had them perform three rounds of human–machine dialogue with a pipeline task-oriented dialogue system or an end-to-end task-oriented dialogue system. We also had another 186 participants do the same with an open-domain dialogue system. We then constructed BERT-based models to predict the personality traits of the participants from the dialogues. The results showed that prediction accuracy was generally better with open-domain dialogue than with task-oriented dialogue, although Extraversion (one of the Big Five personality traits) could be predicted equally well for both open-domain dialogue and pipeline task-oriented dialogue. We also examined the effect of utilizing different types of dialogue on personality prediction by conducting a cross-comparison of the models trained from the task-oriented and open-domain dialogues. As a result, we clarified that the open-domain dialogue cannot be used to predict personality traits from task-oriented dialogue, and vice versa. We further analyzed the effects of system utterances, task performance, and the round of dialogue with regard to the prediction accuracy.

A Mood Semantic Awareness Model for Emotional Interactive Robots.

The rapid development of natural language processing technology and improvements in computer performance in recent years have resulted in the wide-scale development and adoption of human-machine dialogue systems. In this study, the Icc_dialogue model is proposed to enhance the semantic awareness of moods for emotional interactive robots. Equipped with a voice interaction module, emotion calculation is conducted based on model responses, and rules for calculating users' degree of interest are formulated. By evaluating the degree of interest, the system can determine whether it should transition to a new topic to maintain the user's interest. This model can also address issues such as overly purposeful responses and rigid emotional expressions in generated replies. Simultaneously, this study explores topic continuation after answering a question, the construction of dialogue rounds, keyword counting, and the creation of a target text similarity matrix for each text in the dialogue dataset. The matrix is normalized, weights are assigned, and the final text score is calculated. In the text with the highest score, the content of dialogue continuation is determined by calculating a subsequent sentence with the highest similarity. This resolves the issue in which the conversational bot fails to continue dialogue on a topic after answering a question, instead waiting for the user to voluntarily provide more information, resulting in topic interruption. As described in the experimental section, both automatic and manual evaluations were conducted to validate the significant improvement in the mood semantic awareness model's performance in terms of dialogue quality and user experience.

Beyond Words: An Intelligent Human-Machine Dialogue System with Multimodal Generation and Emotional Comprehension

Intelligent service robots have become an indispensable aspect of modern-day society, playing a crucial role in various domains ranging from healthcare to hospitality. Among these robotic systems, human-machine dialogue systems are particularly noteworthy as they deliver both auditory and visual services to users, effectively bridging the communication gap between humans and machines. Despite their utility, the majority of existing approaches to these systems primarily concentrate on augmenting the logical coherence of the system’s responses, inadvertently neglecting the significance of user emotions in shaping a comprehensive communication experience. To tackle this shortcoming, we propose the development of an innovative human-machine dialogue system that is both intelligent and emotionally sensitive, employing multimodal generation techniques. This system is architecturally comprised of three components: (1) data collection and processing, responsible for gathering and preparing relevant information, (2) a dialogue engine, which generates contextually appropriate responses, and (3) an interaction module, responsible for facilitating the communication interface between users and the system. To validate our proposed approach, we have constructed a prototype system and conducted an evaluation of the performance of the core dialogue engine by utilizing an open dataset. The results of our study indicate that our system demonstrates a remarkable level of multimodal generation response, ultimately offering a more human-like dialogue experience.

A multi-message passing framework based on heterogeneous graphs in conversational emotion recognition

As an important development direction of natural language processing, emotion recognition in conversation (ERC) remains a challenge in sentiment analysis. Given the large-scale dialogue datasets and their wide application in the fields of recommendation systems and human–machine dialogue systems, researchers have begun to pay more attention to the issue of ERC. In recent research, the task of ERC has been largely based on the graph structure to model the speaker level. However, most existing studies simply splice multimodal features, and the heterogeneity of multimodal features tends to be overlooked. Hence, this paper proposes a multivariate messaging framework to embed heterogeneous information into multimodal relational graphs. In the process of aggregating graph node information, we take into account the homogeneity of nodes and assign different weights to different nodes so as to better aggregate semantic information. In order to improve the robustness of the model, we utilize the mechanism of sharing weights among neighbors to reduce the number of network parameters and improve the generalization ability of the model. In so doing, the node information is aggregated through the constructed graph network, and the final semantic vector representation is obtained. Experiments over two benchmark datasets for ERC show that our proposed model achieves improved performance in accuracy and F1 value.

Research on Multi-Domain Intelligent Customer Service Dialog Modeling with Integrated Transfer Learning Strategies

Abstract The intelligent customer service dialog model is centered on human-machine dialog, which has good prospects for commercial applications in multiple domains. In this paper, we use the Siamese-LSTM model to do vectorization of questions in the FAQ question and answer database to get the semantic representation vector of sentences, and then use the approximate retrieval algorithm to index the question and answer database and perform approximate nearest-neighbor retrieval of the query. After completing the question query, migration learning is employed to create a mapping between input questions and human responses, enabling the model to produce sentences that are similar to human responses. Tests show that the task success rate gradually stabilizes around 0.80 at about the 100th round and fluctuates up to around 0.986 after that. For the average number of conversation rounds, migration learning improves the conversation efficiency of intelligent customer service, and the average number of conversation rounds gradually stabilizes at about 150 rounds and eventually stabilizes at about 4.2 rounds as the number of training rounds increases. The transfer learning strategy helps machine responses to be as close to human responses as possible.

Job sharing between human professionals and chatbots: How should ‘handovers’ happen?

Job sharing between humans and artificial intelligence (AI) systems is likely to become increasingly common in several domains of work. In this paper, we examine mechanisms for managing job sharing for one particular class of AI system: human–machine dialogue systems, or chatbots. This is a useful case to consider, as several mechanisms for managing job sharing are already emerging in these systems, and these mechanisms draw on those that human professionals already use to share work among themselves. A key concept in this domain is that of a ‘handover’, where a client is passed from one worker to another. We identify different types of handover, for human and AI workers, and discuss a range of issues that govern how these should take place for effective job sharing. We identify several questions that arise for engineers designing dialogue systems that support handover functionality, relating to timing and transparency. We conclude by arguing that handovers provide a useful way for structuring discussions of job sharing between humans and AI systems, in dialogue-based domains and perhaps beyond.

User Interest Based Contextual Conversational Recommender System

The Conversational recommender system is for item recommendation during human-machine dialogue, where items can be movies, music, and goods. Scenarios can be intelligent customer service and shopping assistants. The system's goal is to generate high-quality recommendations in short-round interactions. There are two main problems with the system. Firstly, recommending through dialogues is a hard problem as less contextual information is available, resulting in fewer signals for recommendation and less precision for user interest modeling. Secondly, the recommender system considers the absence of interaction between a user and an item as a negative sample. However, this approach can introduce bias in the objectives because non-interaction could potentially be a positive sample. To tackle the previously mentioned concerns, this paper suggests a new model. This model adds an extra knowledge graph to enrich contextual information. Then, this model introduces contrastive learning to separate the distribution between positive and negative samples and improve learning efficiency. This paper further tests the model on the ReDial dataset, and experiments have shown that the method is effective and performs better than previous work.

A Corpus-Based Study on Feedback in Daily Conversation: Forms, Position and Contexts.

Understanding how feedback is employed in various forms, positions, and contexts can provide valuable insights into improving communication and the design of human-machine dialogue systems. This paper aims to deepen the understanding of feedback in daily conversation and investigate how feedback is employed in various linguistic forms, position, preceding and following contexts, using a large corpus of telephone conversations. The study identifies three subclasses of feedback, including understandings, agreements, and answers, which account for almost one-third of the total utterances in the corpus. Acknowledge (backchannel) is the most frequently used subtype of feedback, accounting for almost 60% of the feedback, and is primarily used for conversational management and maintenance. Assessment/appreciation, on the other hand, is used less frequently, accounting for less than 10% of feedback, and is mainly realized by more creative, unpredictable, longer forms. The analysis also reveals that speakers are intentional in distinguishing the three subclasses of feedback based on various variables, such as position and the proximal discourse environment. Furthermore, the three subclasses of feedback are restricted by the function ofpreceding contexts, which shape the length of the remaining turn. The study suggests that future research should focus on exploring the individual differences and investigating the possible variations across different cultures and languages.

Transition-Relevance Places Machine Learning-Based Detection in Dialogue Interactions

A transition-relevance place (TRP) represents a place in a conversation where a change of speaker can occur. The appearance and use of these points in the dialogue ensures a correct and smooth alternation between the speakers. In the presented article, we focused on the study of prosodic speech parameters in the Slovak language, and we tried to experimentally verify the potential of these parameters to detect TRP. To study turn-taking issues in dyadic conversations, the Slovak dialogue corpus was collected and annotated. TRP places were identified by the human annotator in the manual labelling process. The data were then divided into chunks that reflect the length of the interpausal dialogue units and the prosodic features were computed. In the Matlab environment, we compared different types of classifiers based on machine learning in the role of an automatic TRP detector based on pitch and intensity parameters. The achieved results indicate that prosodic parameters can be useful in detecting TRP after splitting the dialogue into interpausal units. The designed approach can serve as a tool for automatic conversational analysis or can be used to label large databases for training predictive models, which can help machines to enhance human-machine spoken dialogue applications.

Conco-ERNIE: Complex User Intent Detect Model for Smart Healthcare Cognitive Bot

The outbreak of Covid-19 has exposed the lack of medical resources, especially the lack of medical personnel. This results in time and space restrictions for medical services, and patients cannot obtain health information all the time and everywhere. Based on the medical knowledge graph, healthcare bots alleviate this burden effectively by providing patients with diagnosis guidance, pre-diagnosis, and post-diagnosis consultation services in the way of human-machine dialogue. However, the medical utterance is more complicated in language structure, and there are complex intention phenomena in semantics. It is a challenge to detect the single intent, multi-intent, and implicit intent of a patient’s utterance. To this end, we create a high-quality annotated Chinese Medical query (utterance) dataset, CMedQ (about 16.8k queries in medical domain which includes single, multiple, and implicit intents). It is hard to detect intent on such a complex dataset through traditional text classification models. Thus, we propose a novel detect model Conco-ERNIE , using concept co-occurrence patterns to enhance the representation of pre-trained model ERNIE. These patterns are mined using Apriori algorithm and will be embedded via Node2Vec. Their features will be aggregated with semantic features into Conco-ERNIE by using an attention module, which can catch user explicit intents and also predict user implicit intents. Experiments on CMedQ demonstrates that Conco-ERNIE achieves outstanding performance over baseline. Based on Conco-ERNIE, we develop an intelligent healthcare bot, MedicalBot . To provide knowledge support for MedicalBot , we also build a Chinese medical graph, CMedKG (about 45k entities and 283k relationships).

Human-machine dialogue modality of English Language oral skills testing among Chinese EFL students

With the development of computer technology and the development and application of interactive software, more and more second language oral examinations begin to adopt the form of "human-machine dialogue" as the main way of oral examination. However, the results of these experiments have not been validated in the Chinese context. Therefore, this study aims to identify the affecting factors of students’ performance in different English oral tests among Chinese EFL learners. The study used an experimental design. This paper designs and implements a simulated spoken English test of human-machine dialogue modality. 5 Chinese undergraduates students majoring in English language studies and 5 non-English majors are recruited to participate in the experiment. Also, in addition, the experiment also recruited 6 teachers with rich experience in teaching English as a second language as examiners. The results show that there are significant differences in the effective speech frequency in the two tests. Pearson value is.004, and reliability r value is R = 0.04, indicating significant reliability. In terms of hesitation, the duration of all subjects in Q1 and Q2 is significantly different (p<.01). Lexical errors and semantic errors were the most occurred mistakes among students. Finally, the subjects showed high level of anxiety. In terms of self-evaluation of speaking ability, only the group of intermediate English learners show significant differences in the self-evaluation of the two experiments test can truly reflect their oral English ability. This study recommends more research on the human-machine dialogue as the subjects in human-machine dialogue modality cannot get real-time feedback from the communication object, so the subjects are seldom able to notice and self-correct grammatical errors during the expression process. Fourth, the author analyzes and raises research questions about the mistakes made by the subjects in their oral expressions. The human-machine dialogue modality cannot guide the examinees through real-time communication and stimulate the examinees to express the examinee's grasp of relevant second language knowledge which the examiner wants to test.

Anticipating User Intentions in Customer Care Dialogue Systems

In this article, we investigate the case of human-machine dialogues in the specific domain of commercial customer care. We built a corpus of conversations between users and a customer-care chatbot of an Italian Telecom Company, focusing on a sample of conversations where users contact the service asking for explanations about billing issues or overcharges. We observed that users’ requests are often vague, generic or incomprehensible. In such cases, commercial dialogue systems typically ask for clarifications or further details to fully understand users’ specific requests. However, from the corpus analysis it appeared that chatbot's clarifying requests may result in ineffective interactions, with users eventually giving up the conversation or switching to a human agent for a faster query resolution. A recovery strategy is thus needed to anticipate users’ information needs, or intentions. We address this issue resorting to GEN-DS, a dialogue system based on symbolic data-to-text generation. GEN-DS analyzes the user-company contextual relational knowledge, with the aim to generate more relevant answers to unclear questions. In this article, we describe the GEN-DS architecture along with the experiments we carried out to evaluate its output. Results from an offline human evaluation show significant improvements of GEN-DS compared to the original system. These improvements concern properties such as utility, necessity, understandability, and quickness of the information communicated in the dialogue. We believe that GEN-DS techniques may find application in all the dialogue systems that need to manage vague requests and must rely on relational knowledge.

Research on intelligent speech recognition algorithm in UAV ground station

Human-machine dialogue is one of the important components of realizing the intelligent control of UAV. By identifying the pronunciation of the UAV operator, the UAV can be controlled by voice commands instead of manual operation. This method can reduce the operation errors caused by the distraction of UAV operators and improve the combat effectiveness of UAV.Based on the analysis of the flight and mission control requirements of unmanned UAV, this paper establishes an end-to-end speech recognition method based Deep full convolutional neural network (DFCNN) and link sequence classification (connectionist temporal classification,CTC ) for operators in UAV ground stations. The experimental results show that the proposed method can improve the signal-to-noise ratio and its recognition accuracy, effectively solve the speech recognition problem in the UAV ground station environment, and has high practical application value.

Construction of a Safety Management System for University Laboratories Based on Artificial Intelligence and IoT Technology

Based on IoT technology, it can combine the actual needs of the university laboratory system to establish an equipment safety monitoring system, share data in real time, and monitor the operation equipment of university laboratories comprehensively. Through the collection of equipment-related data, we have a comprehensive analysis of data in order to have an accurate judgment of the state of the equipment, so that the chances of equipment failure can be gradually reduced. In this paper from the architectural point of view, IoT contains four layers: perception layer, network layer, platform layer, and application layer. The perception layer mainly solves the problem of data collection, the network layer mainly solves the problem of data transmission, the platform layer mainly solves the problem of data management, and the application layer mainly solves the problem of data value creation. From the technical point of view, the university laboratories’ Internet of Things widely used big data, cloud computing, Internet of Things, artificial intelligence, blockchain, edge computing, and other types of information technology and intelligent technology. From the role, the university laboratories’ IoT is to provide sufficient and effective information and technical support for planning and construction, production and operation, operation and management, integrated services, new business, new model development, enterprise ecosystem construction, and other aspects by bringing together resources from all aspects. The whole university laboratory system sustainability monitoring equipment maintains the continuity of monitoring and can be the first time to staff feedback fault information, to achieve the human-machine dialogue function; staff in the control of equipment safety monitoring system just enter the relevant instructions to fully achieve the purpose of control; staff can also print a certain period of time fault-related information, which will be properly stored in a reasonable location.

Integrating Scene Image and Conversational Text to Develop Human–Machine Dialogue

In recent years, it has become a trend to build social dialogue systems to achieve human–robot interaction. While current conversational systems mostly focus on the dialogue utterances, visual context also plays an important role in determining the relevance of the system responses to the dialogue. In this study, we develop an integrated approach to investigate how to achieve such a visual-language task. Our approach takes both scene images and dialogue utterances into account and trains a neural model to generate machine responses of natural language. We have conducted a series of experiments to evaluate the presented approach, and the results confirm its usefulness and effectiveness.

Desktop Voice Assistant

Abstract: The primary goal of trending technology artificial intelligence (AI) is to realize natural human-machine dialogue. Various IT-based companies also utilized dialogue networks technology to create various types of Virtual Personal Assistants focused on their products and areas for expanding human-machine contact, such as Alexa, Cortana, Google's Assistant, Siri and so more. Just like the Microsoft voice assistant named 'Cortana', we designed our virtual assistant which performs basic tasks based on the instruction provided to it on the Windows platform using Python. Here, Python is used as a scripting language as it has a large library that is used to perform instructions. Using Python packages, a personalized virtual assistant recognizes and processes the user's voice. Voice assistants are a fantastic advancement in the sector of Artificial Intelligence that can transform people's lives in a variety of ways. The voice-based assistant was initially given on cellphones and quickly gained popularity. It was widely acknowledged by all. Previously, voice assistants were largely found in smartphones and laptops, but they are now increasingly available in various home automation setups and smart speakers. Many technologies seem to become wiser in their very own way, allowing them to converse with humans in a simple language. Desktop voice assistants are programme that can identify people's speech and answer through an integrated speech system. This paper will outline how different voice assistants work, as well as their primary challenges and limitations. The way of developing a voice-based assistant without requiring cloud services is discussed in this paper, which would promote the future growth of such devices. Keywords: Voice Assistant, Speech Recognition, Python, Smtplib, Automation.