Detecting Bot-Answerable Questions in Ubuntu Chat
نویسندگان
چکیده
Ubuntu’s Internet Relay Chat technical support channel has bots that output specific messages in response to command words from other channel users. These messages can be used to answer frequently-asked questions instead of requiring an expert to (repeatedly) type a lengthy reply. We describe an approach to automatically distinguish bot-answerable questions, which would mitigate this problem. To the best of our knowledge, this is the first work on investigating question answering in a multiparticipant chat domain. Our results indicate that for some types of questions, supervised learning algorithms perform well on this task and, in addition, that character n-grams are a better representation than traditional bag-of-words for this task and domain.
منابع مشابه
Developing a ChatBot to Answer Spatial Queries for use in Location-based Services
A Chat Bot is an automated operator that can interact with customers like a human operator, answer their questions, solve problems and get feedback. Real-time responsiveness, the sense of talking to a human user is one of their good features that can be used to deliver location-based services. This paper designed a Chat Bot that can talk and answer users' questions based on their location. Thi...
متن کاملCollective emotion dynamics in chats with agents, moderators and Bots
Collective emotion dynamics in chats with agents, moderators and Bots M. Šuvakov1,2, B. Tadić1 1 Department of Theoretical Physics, Jožef Stefan Institute, Jamova 39, 1001 Ljubljana, Slovenia 2 Institute of Physics Belgrade, University of Belgrade, Pregrevica 118, 11080 Beograd, Serbia Received March 27, 2014, in final form April 19, 2014 Using agent-directed simulations, we investigate fluctua...
متن کاملOn a Chat Bot Finding Answers with Optimal Rhetoric Representation
We demo a chat bot with the focus on complex, multi-sentence questions that enforce what we call rhetoric agreement of answers with questions. Chat bot finds answers which are not only relevant by topic but also match the question by style, argumentation patterns, communication means, experience level and other attributes. The system achieves rhetoric agreement by learning pairs of discourse tr...
متن کاملThe Ubuntu Chat Corpus for Multiparticipant Chat Analysis
We present the Ubuntu Chat Corpus as a data source for multiparticipant chat analysis. This addresses the problem of the lack of a large, publicly suitable corpora for research in this medium. The advantages of using this corpus for research is its large number of chat messages, its multiple languages, its technical nature, and all of the original chat messages are in the public domain.
متن کاملChatbots Meet eHealth: Automatizing Healthcare
The aim of this work is to investigate the effectiveness of novel human-machine interaction paradigms for eHealth applications. In particular, we propose to replace usual human-machine interaction mechanisms with an approach that leverages a chat-bot program, opportunely designed and trained in order to act and interact with patients as a human being. Moreover, we have validated the proposed in...
متن کامل