Chatbot

About: Chatbot is a research topic. Over the lifetime, 2415 publications have been published within this topic receiving 24372 citations. The topic is also known as: IM bot & AI chatbot.

Using Theory of Mind to assess users' sense of agency in social chatbots

Abstract: The technological advancements in the field of chatbot research is booming. Despite this, it is still difficult to assess which social characteristics a chatbot needs to have for the user to interact with it as if it had a mind of its own. Review studies have highlighted that the main cause is the low number of research papers dedicated to this question, and the lack of a consistent protocol within the papers that do address it. In the current paper, we suggest the use of a Theory of Mind task to measure the implicit social behaviour users exhibit towards a text-based chatbot. We present preliminary findings suggesting that participants adapt towards this basic chatbot significantly more than when they conduct the task alone (p < .017). This task is quick to administer and does not require a second chatbot for comparison, making it an efficient universal task. With it, a database could be built with scores of all existing chatbots, allowing fast and efficient meta-analyses to discover which characteristics make the chatbot appear more ‘human’.

AVA: A Financial Service Chatbot Based on Deep Bidirectional Transformers

Abstract: We develop a chatbot using Deep Bidirectional Transformer models (BERT) to handle client questions in financial investment customer service. The bot can recognize 381 intents, and decides when to say \textit{I don't know} and escalates irrelevant/uncertain questions to human operators. Our main novel contribution is the discussion about uncertainty measure for BERT, where three different approaches are systematically compared on real problems. We investigated two uncertainty metrics, information entropy and variance of dropout sampling in BERT, followed by mixed-integer programming to optimize decision thresholds. Another novel contribution is the usage of BERT as a language model in automatic spelling correction. Inputs with accidental spelling errors can significantly decrease intent classification performance. The proposed approach combines probabilities from masked language model and word edit distances to find the best corrections for misspelled words. The chatbot and the entire conversational AI system are developed using open-source tools, and deployed within our company's intranet. The proposed approach can be useful for industries seeking similar in-house solutions in their specific business domains. We share all our code and a sample chatbot built on a public dataset on Github.

Arabic Question-Answering via Instance Based Learning from an FAQ Corpus

Abstract: In this paper, we describe a way to access Arabic information using chatbot, without the need for sophisticated natural language processing or logical inference. FAQs are Frequently-Asked Questions documents, designed to capture the logical ontology of a given domain. Any Natural Language interface to an FAQ is constrained to reply with the given Answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic FAQs. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers.

Designing Chatbots with Black Americans with Chronic Conditions: Overcoming Challenges against COVID-19

Abstract: Recently, chatbots have been deployed in health care in various ways such as providing educational information, and monitoring and triaging symptoms. However, they can be ineffective when they are designed without a careful consideration of the cultural context of the users, especially for marginalized groups. Chatbots designed without cultural understanding may result in loss of trust and disengagement of the user. In this paper, through an interview study, we attempt to understand how chatbots can be better designed for Black American communities within the context of COVID-19. Along with the interviews, we performed design activities with 18 Black Americans that allowed them to envision and design their own chatbot to address their needs and challenges during the pandemic. We report our findings on our participants’ needs for chatbots’ roles and features, and their challenges in using chatbots. We then present design implications for future chatbot design for the Black American population.