No description available.

In recent years a type of Conversational User Interface (CUI) called chatbots has been more common, these are integrated and used on various platforms such as Slack, Facebook and Skype. Chatbots are based on Artificial intelligence and are a written conversation between a human and an intelligent system. One example is Microsoft‘s chatbot Zo, a social chatbot aimed to entertain. As chatbots are becoming more commonly occurring, the need to study peoples expectations and demands is important in order to improve the user experience and usages of chatbots. In this paper, a study is presented, looking at the requirements and expectations of a chatbot by novice users. The study showed that onboarding is important in order for users to perform tasks successfully. Onboarding is the process for new users to become successful when adopting a product. In the study, eight participants were exposed to two different chatbots, a human-like and a robot-like, and interviewed about their thoughts and experiences from using it. The chatbots is applied to the case of customer support for insurance. The participants received the tasks; sign a new insurance, cancel an old one, get a recommendation for an pregnancy insurance and react on a notification. The results from the study also illustrate the importance of giving the user feedback in form of summaries, give system status of what is going on, sentences from the chatbot should be with concise information, and being able to handle input independent of the formulation. Regardless of which of the chatbots the participants tried first, they favored the second chatbot because they perceived it as easier to talk to with less misunderstandings. This might indicate a learning curve among the users and hint towards the need to design for onboarding. / Under de senaste åren har en typ av konversations användargränssnitt, så kallade chatbots, blivit mer vanligt förekommande, dessa är integrerade och använda på diverse plattformar t.ex Slack, Facebook och Skype. Chatbots är en baserat på artificiell intelligens och är skriftlig kommunikation mellan en människa och ett intelligent system. Ett exempel är chatboten Zo från Microsoft, det är en social chatbot med syftet att vara underhållande. I takt med att chatbots börjar blir mer vanligt förekommande så ökar även behovet av att studera vilka förväntningar och krav som användare har, för att i sin tur kunna förbättra användandet samt användarupplevelsen av chatbots. I denna artikel presenteras en studie vilken har undersökt vilka krav och förväntningar som nya användare har på chatbots. Studien visade att introduktionsprocessen är viktig för att användare ska kunna utföra uppgifter korrekt. Introduktionsprocessen menar på den process som nya användare går igenom för att bli framgångsrika i användandet när de interagerar med en produkt. I studien, deltog 8st personer som fick testa två stycken olika chatbots, en som var mer människolik och en som var mer robotlik, sedan svara på frågor rörande deras tankar och uppfattningar från att interagera med dessa. Chatbottarna är applicerade inom kundsupport på ett försäkringsbolag. Deltagarna fick uppgifterna; teckna en försäkring, avsluta en gammal försäkring, be om en rekommendation för en gravidförsäkring samt uttrycka vad användaren ansåg om en notifikation. Resultatet från studien visade även på vikten av att ge användare återkoppling i form av summeringar, ge system status av vad som händer, meningar från chatboten ska vara med koncis information samt att systemet ska kunna hantera alla typer av svar oavsett formulering. Oberoende på vilken av de två chatbottarna som användarna interagerade med först, så visade resultatet att deltagarna föredrog den chatbot de interagerade med sist pga att den uppfattades som lättare att prata med samt att det blev färre missförstånd. Detta tycks tyda på en inlärningskurva hos användarna vilket visar på behovet av att designa för inlärningsprocessen.

yes / This paper presents a critical evaluation framework for a linguistically motivated conversational software agent (CSA). The CSA prototype investigates the integration, intersection and interface of the language, knowledge, and speech act constructions (SAC) based on a grammatical object, and the sub-model of belief, desires and intention (BDI) and dialogue management (DM) for natural language processing (NLP). A long-standing issue within NLP CSA systems is refining the accuracy of interpretation to provide realistic dialogue to support human-to-computer communication. This prototype constitutes three phase models: (1) a linguistic model based on a functional linguistic theory – Role and Reference Grammar (RRG), (2) an Agent Cognitive Model with two inner models: (a) a knowledge representation model, (b) a planning model underpinned by BDI concepts, intentionality and rational interaction, and (3) a dialogue model. The evaluation strategy for this Java-based prototype is multi-approach driven by grammatical testing (English language utterances), software engineering and agent practice. A set of evaluation criteria are grouped per phase model, and the testing framework aims to test the interface, intersection and integration of all phase models. The empirical evaluations demonstrate that the CSA is a proof-of-concept, demonstrating RRG’s fitness for purpose for describing, and explaining phenomena, language processing and knowledge, and computational adequacy. Contrastingly, evaluations identify the complexity of lower level computational mappings of NL – agent to ontology with semantic gaps, and further addressed by a lexical bridging solution.

As research in Artificial Intelligence (AI) advances, it is crucial to focus on having seamless communication between humans and machines in order to effectively accomplish tasks. Smooth human-machine communication requires the machine to be sensible and human-like while interacting with humans, while simultaneously being capable of extracting the maximum information it needs to accomplish the desired task. Since a lot of the tasks required to be solved by machines today involve the understanding of images, training machines to have human-like and effective image-grounded conversations with humans is one important step towards achieving this goal. Although we now have agents that can answer questions asked for images, they are prone to failure from confusing input, and cannot ask clarification questions, in turn, to extract the desired information from humans. Hence, as a first step, we direct our efforts towards making Visual Question Answering agents human-like by making them resilient to confusing inputs that otherwise do not confuse humans. Not only is it crucial for a machine to answer questions reasonably, it should also know how to ask questions sequentially to extract the desired information it needs from a human. Hence, we introduce a novel game called the Visual 20 Questions Game, where a machine tries to figure out a secret image a human has picked by having a natural language conversation with the human. Using deep learning techniques like recurrent neural networks and sequence-to-sequence learning, we demonstrate scalable and reasonable performances on both the tasks. / Master of Science / Research in Artificial Intelligence has reached to a point where computers can answer natural freeform questions asked to arbitrary images in a somewhat reasonable manner. These machines are called Visual Question Answering agents. However, they are prone to failure from even a slightly confusing input. For example, for an obviously irrelevant question asked to an image, they would answer something non-sensical instead of recognizing that the question is irrelevant. Furthermore, they also cannot ask questions in turn to humans for clarification or for more information. These shortcomings not only harm their efficacy, but also harm their perceived trust from human users. In order to remedy these problems, we first direct our efforts towards making Visual Question Answering agents capable of identifying an irrelevant question for an image. Next, we also try to train machines to be able to ask questions to extract more information from humans to make an informed decision. We do this by introducing a novel game called the Visual 20 Questions game, where a machine tries to figure out a secret image a human has picked by having a natural language conversation with the human. Deep learning techniques such as sequence-to-sequence learning using recurrent neural networks make it possible for machines to learn how to converse based on a series of conversational exchanges made between two humans. Techniques like reinforcement learning make it possible for machines to better themselves based on rewards it gets for accomplishing a task in a certain way. Using such algorithms, we demonstrate promise towards scalable and reasonable performances on both the tasks.

No / This paper analyses different definitions of mobile learning which have been proposed by various researchers. The most distinctive features of mobile learning are extracted to propose a new definition for Mobile Educational Mixed Reality Games (MEMRG). A questionnaire and a quantifying scale are designed to assist the game developers in designing MEMRG. A new psycho-pedagogical approach to teaching is proposed for MEMRG. This methodology is based on the theme of "conversation" between different actors of the learning community with the objective of building the architectural framework for MEMRG.

The rise of conversational generative AI chatbots such as ChatGPT and Gemini is revolutionizing online interactions. Previous research has identified five categories of uses and gratifications (U&G) for users engaging with these chatbots: information seeking, task efficiency, social interaction, entertainment, and personalization. Despite the wide range of use cases, most chatbots provide one-size-fits-all text-based interactions, neglecting user preferences. Recent advancements are progressively introducing interactive features that empower users to control their interactions, such as choosing a preferred conversational style. However, despite these improvements in the industry, the interactivity in gen AI chatbots remains underexplored. This thesis serves as a user-centric foundational study of user engagement with gen AI chatbots by understanding users’ context of use across the five U&G dimensions, analyzing the limitations of text-based interactions, and proposing practical suggestions for desired interactive features.

Yes / This chapter discusses a linguistically orientated model of a conversational software agent (CSA) (Panesar 2017) framework sensitive to natural language processing (NLP) concepts and the levels of adequacy of a functional linguistic theory (LT). We discuss the relationship between NLP and knowledge representation (KR), and connect this with the goals of a linguistic theory (Van Valin and LaPolla 1997), in particular Role and Reference Grammar (RRG) (Van Valin Jr 2005). We debate the advantages of RRG and consider its fitness and computational adequacy. We present a design of a computational model of the linking algorithm that utilises a speech act construction as a grammatical object (Nolan 2014a, Nolan 2014b) and the sub-model of belief, desire and intentions (BDI) (Rao and Georgeff 1995). This model has been successfully implemented in software, using the resource description framework (RDF), and we highlight some implementation issues that arose at the interface between language and knowledge representation (Panesar 2017).

Cette thèse prend pour objet des situations d’apprentissage guidé du français, en face à face et en dehors de cadres institutionnels, se déroulant dans le contexte multilingue du Luxembourg. Elle décrit et analyse des interactions entre des locuteurs plurilingues adultes dont la première langue est le chinois ou le coréen et des locuteurs plurilingues agissant en tant qu’experts pour la langue française. Plus particulièrement, dans l’optique d’une analyse qualitative des données, ce travail s’efforce d’appliquer les outils de l’analyse conversationnelle d’inspiration plutôt anglo-américaine à une vision didactique de tradition de langue française. Pour ce faire, il est fait appel aux notions de compétence communicative (Hymes 1972), de dramatisation (Goffman 1991) et de rôle social (Cicurel 1988). L’analyse montre que dans des situations d’apprentissage-en-interaction, les apprenants et les experts ont recours à une diversité de ressources interactionnelles liées à des activités de dramatisation : le dialogue-en-situation, la voix, la séquence préfabriquée, la séquentialité discursive, la réparation, la séquence explicative, le récit préenregistré, l’évaluation, le récit enchâssé, l’identité, le récit conversationnel de l’expert, l’interview, le récit conversationnel de l’apprenant et le mode éditeur. Pour conclure, un rapprochement est opéré entre ces activités de dramatisation et la didactique du FLE, à plusieurs niveaux, sous la forme de recommandations suggestions. / The current thesis focuses on guided language learning exchanges in French, in a face-to-face non-institutional setting in the multilingual context of Luxembourg. It describes and analyzes interactions between adult plurilingual speakers whose first language is Chinese or Korean and multilingual speakers acting as experts for the French language. Taking a qualitative analysis approach, our work strives to apply the tools of conversation analysis of a rather Anglo-American origin to a vision of “didactique” corresponding to the French language tradition. To this end, we rely in particular on the notions of communicative competence(Hymes 1972), dramatization (Goffman 1991) and social role (Cicurel 1988). The analysis of learning-in-interaction data shows the enactment of a variety of dramatization-related interactional resources by both learners and experts: the situated dialogue, the voice, the formulaic language, the discursive sequentiality, the repair, the explanatory sequence, the pre-recorded conversational narrative, the evaluation, the embedded narrative, the identity, the conversational narrative of the expert, the interview, the conversational narrative of the learner and the editor mode. A few recommendations-suggestions are proposed in the conclusion, focusing on how these dramatization activities could inform, at different levels, the development of French teaching and learning.

Work email is one of the organisations most critical tool today. It`s have become a standard way to communicate internally and externally. It can also affect our well-being. Email overload has become a well-known issue for many people. With interviews, follow up interviews, and a workshop, three persons from an accounting firm prioritise pre-define emails needs. And identified several other email needs that were added to the priority list. A thematic analysis and summarizing of a Likert scale was conducted to identify underlying work email needs and work email needs that are not apparent. Three work email needs were selected and using scenario-based methods and the elements of PACT to investigating how the characteristics of a chatbot can help solve the identified work email overload issue? The result shows that email overload is percept different from individual to individual. The choice of how email is handled and email activities indicate how email overload feeling is experienced. The result shows a need to get a sense of the email content quickly, fast collect financial information and information from Swedish authorities, and repetitive, time-consuming tasks. Suggestions on how this problem can be solved have been put forward for many years, and how to use machine learning to help reduce email overload. However, many of these proposed solutions have not yet been implemented on a full scale. One conclusion may be that since email overload is not experienced in the same way, individuals have different needs - One solution does not fit all. With the help of the character of a chatbot, many problems can be solved. And with a technological character of a chatbot that can learn individuals' email patterns, suggest email task to the user and performing tasks to reducing the email overload perception. Using keyword for email intents to get a sense of the email content faster and produce quick links where to find information about the identified subject. And to work preventive give the user remainder and perform repetitive tasks on specific dates.

No description available.