scispace - formally typeset
Search or ask a question
Topic

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.


Papers
More filters
Posted Content
TL;DR: This paper proposes a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to aresource-poor target domain and proposes an efficient and effective hybrid model by combining a sentence encoding- based method and a sentence interaction-based method as the base model.
Abstract: In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain. Specifically, since most existing transfer learning methods only focus on learning a shared feature space across domains while ignoring the relationship between the source and target domains, we propose to simultaneously learn shared representations and domain relationships in a unified framework. Furthermore, we propose an efficient and effective hybrid model by combining a sentence encoding- based method and a sentence interaction-based method as our base model. Extensive experiments on both paraphrase identification and natural language inference demonstrate that our base model is efficient and has promising performance compared to the competing models, and our transfer learning method can help to significantly boost the performance. Further analysis shows that the inter-domain and intra-domain relationship captured by our model are insightful. Last but not least, we deploy our transfer learning model for PI into our online chatbot system, which can bring in significant improvements over our existing system. Finally, we launch our new system on the chatbot platform Eva in our E-commerce site AliExpress.

18 citations

Journal ArticleDOI
TL;DR: This work proposes a knowledge-grounded chatbot model that effectively reflects the dialogue context and given knowledge by using well-designed attention mechanisms and shows better performances than the state-of-the-art model in a variety of measures.
Abstract: A conversation is based on internal knowledge that the participants already know or external knowledge that they have gained during the conversation. A chatbot that communicates with humans by using its internal and external knowledge is called a knowledge-grounded chatbot. Although previous studies on knowledge-grounded chatbots have achieved reasonable performance, they may still generate unsuitable responses that are not associated with the given knowledge. To address this problem, we propose a knowledge-grounded chatbot model that effectively reflects the dialogue context and given knowledge by using well-designed attention mechanisms. The proposed model uses three kinds of attention: Query-context attention, query-knowledge attention, and context-knowledge attention. In our experiments with the Wizard-of-Wikipedia dataset, the proposed model showed better performances than the state-of-the-art model in a variety of measures.

18 citations

Book ChapterDOI
27 Oct 2019
TL;DR: The main purpose of this paper is to outline the methodology that guided the implementation of a virtual assistant so that it can be reproduced in different educational contexts and study chatbots as tools for learning.
Abstract: We developed a virtual assistant that enables students to access interactive content adapted for an introductory undergraduate course on artificial intelligence. This chatbot is able to show answers to frequently asked questions in a hierarchical structured manner, leading students by either voice, text or tactile input to the content that better solves their questions and doubts. It was developed using Google Dialogflow as a simple way to generate and train a natural language model. Another convenience of this platform is its ability to collect usage data that is potentially useful for lecturers as learning indicators. The main purpose of this paper is to outline the methodology that guided our implementation so that it can be reproduced in different educational contexts and study chatbots as tools for learning. At the moment, several articles, news and blogs are writing about the potential, implementation and impact chatbots have in general contexts, however there is little to no literature proposing a methodology to reproduce them for educational purposes. In that respect, we developed four main categories as a generic structure of course content and focused on quick implementation, easy updating and generalization. The final product received a general approbation of the students due to its accessibility and well structured data.

18 citations

Posted Content
TL;DR: A chatbot using Deep Bidirectional Transformer models (BERT) to handle client questions in financial investment customer service, and a discussion about uncertainty measure for BERT, where three different approaches are systematically compared on real problems.
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 "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.

18 citations

Journal ArticleDOI
TL;DR: In this paper , an exploratory study aimed to create an inventory of affordances that chatbots provide in the primary English as a foreign language (EFL) classroom and explore how the affordances affect psychological aspects in language learners, particularly regarding their motivation to learn English through chatbots.
Abstract: Professionals within the field of language learning have predicted that chatbots would provide new opportunities for the teaching and learning of language. Despite the assumed benefits of utilizing chatbots in language classrooms, such as providing interactional chances or helping to create an anxiety-free atmosphere, little is known about learners’ actual use of chatbots during language classes or how chatbots affect their motivation to learn a language. To address these gaps, this exploratory study aimed to create an inventory of affordances that chatbots provide in the primary English as a foreign language (EFL) classroom and to explore how the affordances affect psychological aspects in language learners, particularly regarding their motivation to learn English through chatbots. Thirty-six Korean primary school learners participated in a 16-week EFL course that utilized customized chatbots. These chatbots were created using Google’s Dialogflow. After the course, individual in-depth interviews were conducted regarding the participants’ experiences and perceptions of the chatbots. Student-chatbot interaction logs produced during the course were also collected to supplement the interview data. Qualitative analysis of the interview transcripts and interaction logs revealed the presence of pedagogical, technological, and social affordances. Depending on the learner, the chatbot affordances were perceived differently; thus, each affordance acted as either an opportunity or a constraint for English language learning. In addition, this study specifically discussed how these chatbot affordances might have affected psychological states in language learners. Future recommendations regarding the use of chatbots in language classrooms were suggested from both pedagogical and technological perspectives.

18 citations


Network Information
Related Topics (5)
User interface
85.4K papers, 1.7M citations
79% related
Mobile computing
51.3K papers, 1M citations
78% related
Social media
76K papers, 1.1M citations
78% related
Encryption
98.3K papers, 1.4M citations
76% related
Web service
57.6K papers, 989K citations
76% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023916
20221,413
2021564
2020617
2019528
2018326