Search

Several studies have addressed the importance of context and users’ knowledge and experience in quantifying the usability and effectiveness of the explanations generated by explainable artificial intelligence (XAI) systems. However, to the best of our knowledge, no component-agnostic system that accounts for this need has yet been built. This paper describes an approach called ConvXAI, which can create a dialogical multimodal interface for any black-box explainer by considering the knowledge and experience of the user. First, we formally extend the state-of-the-art conversational explanation framework by introducing clarification dialogue as an additional dialogue type. We then implement our approach as an off-the-shelf Python tool. To evaluate our framework, we performed a user study including 45 participants divided into three groups based on their level of technology use and job function. Experimental results show that (i) different groups perceive explanations differently; (ii) all groups prefer textual explanations over graphical ones; and (iii) ConvXAI provides clarifications that enhance the usefulness of the original explanations.

Despite important progress, conversational systems often generate dialogues that sound unnatural to humans. We conjecture that the reason lies in the different training and testing conditions: agents are trained in a controlled “lab” setting but tested in the “wild”. During training, they learn to utter a sentence given the ground-truth dialogue history generated by human annotators. On the other hand, during testing, the agents must interact with each other, and hence deal with noisy data. We propose to fill this gap between the training and testing environments by training the model with mixed batches containing both samples of human and machine-generated dialogues. We assess the validity of the proposed method on GuessWhat?!, a visual referential game. We show that our method improves the linguistic quality of the generated dialogues, and it leads to higher accuracy of the guessing task; simple perturbations of the ground-truth dialogue history that mimic machine-generated data do not account for a similar improvement. Finally, we run a human evaluation experiment on a sample of machine-machine dialogues to complement the quantitative analysis. This experiment shows that also human annotators successfully exploit dialogues generated by a model trained with mixed batches to solve the task. Hence, the mixed-batch training does not cause a language drift. Moreover, we find that the new training regime allows human annotators to be significantly more confident when selecting the target object, showing that the generated dialogues are informative.

Humans are living in an era where they are interacting with machines day in and day out. In this new era of the 21st century, a virtual assistant (IVA) is a boon for everyone. It has opened the way for a new world where devices can interact their own. The human voice is integrated with every device making it intelligent. These IVAs can also be used to integrate it with business intelligence software such as Tableau and PowerBI to give dashboards the power of voice and text insights using NLG (natural language generation). This new technology attracted almost the entire world like smart phones, laptops, computers, smart meeting rooms, car InfoTech system, TV, etc. in many ways. Some of the popular voice assistants are like Mibot, Siri, Google Assistant, Cortana, Bixby, and Amazon Alexa. Voice recognition, contextual understanding, and human interaction are some of the issues that are continuously improving in these IVAs and shifting this paradigm towards AI research. This research aims at processing human natural voice and gives a meaningful response to the user. The questions that it is not able to answer are stored in a database for further investigation.

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.

Dissertação de mestrado integrado em Engenharia Informática, Tutores artificiais são agentes de software que auxiliam nos processos de ensino e formação. Nos dias de hoje, esses sistemas têm como objetivo fornecer instruções aos alunos sem a intervenção direta de um professor. Para que isso aconteça com sucesso, é necessário que estes sistemas possuam um sistema de conversação que seja capaz de interagir com os alunos de forma simples e cativante, mantendo um diálogo adequado em todos os momentos de ensino que concedem. Essencialmente, os sistemas de conversação são assistentes virtuais que utilizam interfaces de comunicação que interagem com os utilizadores através de frases escritas e orais, e, geralmente, possuem a capacidade de compreender o utilizador. Por norma, o computador assume o papel de professor. No entanto, o aluno também “ensina” o sistema fornecendo dados e a sua perspetiva em relação ao problema, que podem posteriormente ser utilizados para personalizar o seu ensino. É neste contexto que foram realizados os trabalhos desta dissertação, cujo principal objetivo foi a implementação de um componente de conversação para um sistema educacional, que fosse capaz de criar novas dinâmicas entre o sistema e o utilizador, incentivando-o, assim, a despender mais tempo na ferramenta., Artificial tutors are software agents that assist in teaching and training processes. Nowadays, these systems aim to provide instructions to students without the direct intervention of a teacher. For this to happen successfully, these systems must have a conversational system that can interact with the students simply and engagingly while maintaining a fitting dialogue in all moments the user goes through. Conversational systems are virtual assistants that use communication interfaces that interact with users using written and oral phrases, generally having the ability to understand the user. By default, the computer assumes the role of a teacher, however, the students can also "teach" the system by providing data and their perspective on the problem, which can be used later to customize their teaching. It is in this context that the work of this dissertation will be carried out, which will have the main objective of implementing a dialogue component for an Educational System capable of creating new dynamics between the system and the user, thus encouraging the user to spend more time using the tool.

The world has become multimodal. In addition to text, we have been sharing a huge amount of multimedia information in the form of images and videos on the Internet. The wide spread use of smart mobile devices has also changed the way we interact with the Internet. It is now natural for us to capture images and videos freely and use as part of a query, in addition to the traditional text and voices. These, along with the rapid advancements in multimedia, natural language processing, information retrieval, and conversation technologies, mean that it is time for us to explore multimodal conversation and its roles in search and recommendation. Multimodal conversation has the potential to help us to uncover and digest the huge amount of multimedia information and knowledge hidden within many systems. It also enables a natural 2-way interactions between humans and machines, with mutual benefits in enriching their respective knowledge. Finally, it opens up the possibilities of disrupting many existing applications and launching new innovative applications. This panel is timely and aims to explore this emerging trend, and discuss its potential benefits and pitfalls to society. The panel will also explore the limitations of current technologies and highlight future research directions towards developing a multimedia conversational system.

Studies of interaction log analysis are a common tool to investigate behavioural data and contribute to insights into users’ interaction patterns with a system [11, 18]. We present a log analysis from a bespoke conversational system, RealSAM1, an audio-only interaction media assistant in which users can navigate and interact with media content through natural language. The novel assistant is designed for people with a vision impairment or other disability that prevents a person from accessing printed material. The exploratory analysis was conducted to provide an initial insight into the communication and interaction behaviours. We focus on understanding how users utilise the application. The results are twofold, we highlight the (i) implications for the design of future voice-enabled systems such as “infinite-reading” mode, enhanced interaction management enabling file navigation or time-compression techniques, and (ii) challenges of analysing conversational logs and suggest guidelines making these logs more accessible for future research.

In recent years, legal case retrieval has attracted much attention in the IR research community. It aims to retrieve supporting cases for a given query case and contributes to better legal systems. While using a legal case retrieval system, users always feel difficult to construct accurate queries to express their information need, especially when they lack sufficient domain knowledge. Since conversational search has been widely recognized to fulfill users' complex and exploratory information need, we investigate whether conversational search paradigm can be adopted to improve users' legal case retrieval experience. We design a laboratory-based study to collect users' interaction behaviors and explicit feedback signals while using traditional and agent-mediated conversational legal case retrieval systems. Based on the collected data, we compare search behavior and outcome of these two different kinds of interaction paradigms. Compared with the traditional one, experimental results show that users can achieve better retrieval performance with the conversational case retrieval system. Moreover, conversational system can also save users' efforts in formulating queries and examining results.

El presente artículo surge de la revisión documental que pretende indagar por el lugar de la pregunta en las escuelas posmodernas de la terapia familiar sistémica. Se realizó una revisión partiendo de artículos de investigación documental, bibliotecas y otros medios de información como las bases de datos especializadas. De esta revisión, surgieron cuatro categorías de análisis; estas fueron: noción de posmodernidad en contextos interdisciplinarios, escuelas posmodernas, la pregunta y la terapia familiar sistémica. Se concluye que la pregunta ocupa un lugar fundamental en las escuelas posmodernas de terapia familiar sistémica, donde es utilizada por cada escuela con objetivos y formas diferentes. La pregunta es asumida no solo como instrumento, sino como parte del sistema terapéutico donde se posibilita la interacción y la creación de nuevos significados a través de un sistema conversacional entre el cliente y el terapeuta.

In the next wave of insurgence, humans may endeavour self-reflection which can lead to an effortless talk and to find out if an event will fructify. Training the system on how to make accurate prognostication with the help of machine learning and statistical models can lead to an intelligent personalized conversational system. The Chatbot industry is ever-growing and after the COVID-19 pandemic and rigorous lockdowns all around the world, people have realized the importance of human interaction in their lives. We are developing this model to create a more intimate relationship between the system and humans. For this purpose, many open-source platforms are available. Artificial Intelligence Markup Language (AIML) is derived from Extensible Markup Language (XML) which is used to build up a conversational agent artificially. The success of this project will help the model in observing and understanding human emotions which will ultimately help it to form a more personalized relationship to delineate the future course of events.

Despite the increasing presence of conversational agents (CAs) in our daily lives, the lack of information and technology behind them prevents CAs from answering many questions. One of the most typical problems facing conversational user interfaces today is that they often disappoint people by giving the same answer (e.g., “I don't know”). In this work, we focused on situations in which CAs do not provide a proper answer because of a lack of information. Under these situations, we aimed to find more effective answer strategies for CAs to provide people better user experiences. We tested four different response strategies using different degrees of inferences and information as ground. We found differences in usability and user experience depending on how CAs respond. Our results will help designers understand how people feel about the way CAs respond and create better CA responses in situations where it is difficult to provide accurate answers.

This paper describes how machine learning training data and symbolic knowledge from curators of conversational systems can be used together to improve the accuracy of those systems and to enable better curatorial tools. This is done in the context of a real-world practice of curators of conversational systems who often embed taxonomically-structured meta-knowledge into their documentation. The paper provides evidence that the practice is quite common among curators, that is used as part of their collaborative practices, and that the embedded knowledge can be mined by algorithms. Further, this meta-knowledge can be integrated, using neuro-symbolic algorithms, to the machine learning-based conversational system, to improve its run-time accuracy and to enable tools to support curatorial tasks. Those results point towards new ways of designing development tools which explore an integrated use of code and documentation by machines.

As the complexity of intelligent environments grows, there is a need for more sophisticated and flexible interfaces. Conversational systems constitute a very interesting alternative to ease the users’ workload when interacting with such environments, as they can operate them in natural language. A number of commercial toolkits for their implementation have appeared recently. However, these are usually tailored to specific implementations of the processes involved for processing the user’s utterance and generate the system response. In this paper, we present a modular architecture to develop conversational systems by means of a plug-and-play paradigm that allows the integration of developers’ specific implementations and commercial utilities under different configurations that can be adapted to the specific requirements for each system.

Conversational Systems (CSs) are increasingly being used and receiving investments. However, these systems can present problems that discourage users from using them. This paper aims to verify the opinions of Brazilian users and ex-users of CSs about the use of these systems and their possible difficulties. We conducted an online survey with several questions about the use of CSs and obtained 113 respondents from different knowledge areas, such as law, agronomy, health, computing, among others. Results reveal some issues in the Brazilian context that negatively influence the use of CSs, such as accent, lack of support for the Portuguese language, and internet access problems. Despite this, results show that respondents consider CSs easy to use and satisfactory. We hope our results can contribute to improving these systems for the Brazilian context, providing insights for the exploration of new strategies for designers and developers.

We report the results of a crowdsourcing user study for evaluating the effectiveness of human-chatbot collaborative conversation systems, which aim to extend the ability of a human user to answer another person's requests in a conversation using a chatbot. We examine the quality of responses from two collaborative systems and compare them with human-only and chatbot-only settings. Our two systems both allow users to formulate responses based on a chatbot's top-ranked results as suggestions. But they encourage the synthesis of human and AI outputs to a different extent. Experimental results show that both systems significantly improved the informativeness of messages and reduced user effort compared with a human-only baseline while sacrificing the fluency and humanlikeness of the responses. Compared with a chatbot-only baseline, the collaborative systems provided comparably informative but more fluent and human-like messages.

We would like to thank the support of the Spanish Plan for the Advancement of Language Technology (https://www.plantl.gob.es/) and the Secretaría de Estado para la Digitalización e Inteligencia Artificial (SEDIA). This research has also received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 823907 (MENHIR project: https://menhir-project.eu)., The aim of this paper is to present a preliminary scientometric study of the area of conversational systems in Spain. In order to do so, we have used the Web of Science database to retrieve the papers in the area using a comprehensive list of keywords and considering those papers with at least one author with Spanish affiliation. Our results present an overview of the main topics, authors and institutions involved in conversational system research and show the good status of Spanish research in this discipline.

Museums and Art exhibition spaces are adopting Artificial Intelligence (AI) systems to engage and attract visitors in several contexts. The use of AI can boost visitors’ attention, promote informal learning through conversations in front of the exhibits, and motivate visitors to act socially. In this paper, we describe a voice-based conversational system Iris+, in which visitors are inquired to answer questions to an agent. It is a proactive agent that invites visitors to reflect and take action to improve future world. First, we will describe how this system works. Second, we will show the outcomes of evaluation studies with visitors in situ and, a survey shows how visitors engaged in social action after interacting with IRIS+ and public demographics. Based on those visitors’ studies, we propose a set of challenges to design conversational systems in public spaces and the improvements were incorporated into the redesign of IRIS++.

Reminiscence therapy is a non-pharmacological intervention that helps mitigate unstable psychological and emotional states in patients with Alzheimer’s disease, where past experiences are evoked through conversations between the patients and their caregivers, stimulating autobiographical episodic memory. It is highly recommended that people with Alzheimer regularly receive this type of therapy. In this paper, we describe the development of a conversational system that can be used as a tool to provide reminiscence therapy to people with Alzheimer’s disease. The system has the ability to personalize the therapy according to the patients information related to their preferences, life history and lifestyle. An evaluation conducted with eleven people related to patient care (caregiver = 9, geriatric doctor = 1, care center assistant = 1) shows that the system is capable of carrying out a reminiscence therapy according to the patient information in a successful manner.

We present a new solution towards building a crowd knowledge enhanced multimodal conversational system for travel. It aims to assist users in completing various travel-related tasks, such as searching for restaurants or things to do, in a multimodal conversation manner involving both text and images. In order to achieve this goal, we ground this research on the combination of multimodal understanding and recommendation techniques which explores the possibility of a more convenient information seeking paradigm. Specifically, we build the system in a modular manner where each modular construction is enriched with crowd knowledge from social sites. To the best of our knowledge, this is the first work that attempts to build intelligent multimodal conversational systems for travel, and moves an important step towards developing human-like assistants for completion of daily life tasks. Several current challenges are also pointed out as our future directions.

There are several service-oriented models, where services are deployed for the user. The user chooses any one of them. During the operational life cycle of these services, there are several issues that occur. User wants an interface for complaint. This paper uses the sentence boundary detection, NER, document categorization, and sentiment extraction methodologies. The natural language processing generates the training model which is a statistical representation of current system knowledge. When a user enters the input then training model extracts the value of a different parameter, these parameters used by call center model for better understanding of user input. The machine learning model used to generate a logical response. When the time exceeds the size of sample, data should be increased and the model understanding also more and more accurate. The accuracy of the model depends on the size of the sample training data. When training data size increases the statistical model for the call center is updated. When the user interacts with the call center agent then call center agent to extract the value of all parameters based on the current statistical model which is based on the sample training data. The paper uses different parameter such as NER, Document category, and sentiment for making a better user interaction. The probability of correct response is increase n time if n parameters are used for response generation. Call center module to take help from sentence detection, NER, document categorization and sentiment training model for extraction the value of the parameter. These parameter value helpful for extracting the NLP Text meaning. The response correctness also increases whenever anyone parameter is extracted correctly. The maximum entropy approach is used for making statistical modeling. The training data are taken from the heterogeneous source.

Conversational agents have the potential to support users in many tasks. However, support for productivity and well-being in the workplace has received little attention. We present the first design of a conversational system that supports information workers with multiple work-related goals, informed by a survey of the current and potential use of conversational agents in the workplace. The goals of this research include the evaluation of using an agent for scheduling and prioritizing tasks, switching tasks, providing break reminders, dealing with social media distractions and for end of the day reflection on tasks accomplished. We deployed a chat-based intelligent agent, named Amber, in a field study with 24 information workers over the course of 6 days. We present our preliminary findings from the field study and discuss implications for the design of future workplace conversational agents

M-Path is an embodied conversational agent developed to achieve natural interaction using empathic behaviors. This paper is aimed to describe the details of the conversational management system within the M-Path framework that manages dialogue interaction with an emotional awareness. Our conversational system is equipped with a goal-directed narrative structure that adapts to the emotional reactions of the user using empathy mechanisms. We further show the implementation and a preliminary evaluation of our system in a consultation scenario, where our agent uses text-based dialogue interaction to conduct surveys.

How does the presence of an audience influence the social interaction with a conversational system in a physical space? To answer this question, we analyzed data from an art exhibit where visitors interacted in natural language with three chatbots representing characters from a book. We performed two studies to explore the influence of audiences. In Study 1, we did fieldwork cross-analyzing the reported perception of the social interaction, the audience conditions (visitor is alone, visitor is observed by acquaintances and/or strangers), and control variables such as the visitor's familiarity with the book and gender. In Study 2, we analyzed over 5,000 conversation logs and video recordings, identifying dialogue patterns and how they correlated with the audience conditions. Some significant effects were found, suggesting that conversational systems in physical spaces should be designed based on whether other people observe the user or not.

[Resumen] El objetivo de este trabajo fin de grado es el desarrollo e implementación de un asistente virtual para el sitio web de la Facultad de Informática de la Universidad de A Coruña (UDC). Los usuarios serán capaces de interactuar con el asistente, tanto por entrada de texto como a través de voz, y le podrán pedir información sobre cualquier apartado de la web. Para promover el uso generalizado del asistente, se encontrará disponible tanto en gallego como en español. El proyecto seguirá una metodología que incluye todos los ciclos que corresponden a un proyecto software, desde un análisis previo para conocer los objetivos principales del proyecto, planificación, pasando por el diseño, implementación y pruebas. Con este trabajo se ha conseguido un sistema que implementa y demuestra las funcionalidades de un sistema conversacional. [Abstract] The objective of this end-of-degree project is to develop and implement a virtual assistant for the website of the College of Informatic Engineers of the University of A Coruña (UDC). Users will be able to interact with the assistant, both by keyboard inputs and voice, so they will be able to ask for any information of the different sections of the website. In accordance with the promotion of the generalized use of the assistant, its use will be available for both Galician and Spanish. The project will follow a methodology that includes all the software steps that correspond to a project with this characteristics, from a analysis that allows to know the main objectives of the projet, planning, through the design, implementation and finally testing. Most of the development was carried out following a framework that was planned in the initial phase of the project. With this work, it was achieved a system that implements and demonstrated the functionalities of a question answering process with an virtual assistant as its interface. Traballo fin de grao (UDC.FIC). Enxeñaría informática. Curso 2018/2019

In recent years, the task of Question Answering over passages, also pitched as a reading comprehension, has evolved into a very active research area. A reading comprehension system extracts a span of text, comprising of named entities, dates, small phrases, etc., which serve as the answer to a given question. However, these spans of text would result in an unnatural reading experience in a conversational system. Usually, dialogue systems solve this issue by using template-based language generation. These systems, though adequate for a domain specific task, are too restrictive and predefined for a domain independent system. In order to present the user with a more conversational experience, we propose a pointer generator based full-length answer generator which can be used with most QA systems. Our system generates a full length answer given a question and the extracted factoid/span answer without relying on the passage from where the answer was extracted. We also present a dataset of 315000 question, factoid answer and full length answer triples. We have evaluated our system using ROUGE-1,2,L and BLEU and achieved 74.05 BLEU score and 86.25 Rogue-L score.

Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat agents. In particular, we want a conversational system to chat naturally with human and proactively guide the conversation to a designated target subject. The problem is challenging as no public data is available for learning such a target-guided strategy. We propose a structured approach that introduces coarse-grained keywords to control the intended content of system responses. We then attain smooth conversation transition through turn-level supervised learning, and drive the conversation towards the target with discourse-level constraints. We further derive a keyword-augmented conversation dataset for the study. Quantitative and human evaluations show our system can produce meaningful and effective conversations, significantly improving over other approaches., ACL 2019. Data and code available at https://github.com/squareRoot3/Target-Guided-Conversation. fixed typos