TitleDetecting bot-answerable questions in Ubuntu chat
Publication TypeConference Paper
Year of Publication2013
AuthorsUthus, DC, Aha, DW
Conference NameInternational Joint Conference on Natural Language Processing
PublisherACL
Conference LocationNagoya, Japan
KeywordsChat highlighting, machine learning
Abstract

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.

Refereed DesignationRefereed
Full Text
pdf: 
http://www.nrl.navy.mil/itd/aic/sites/www.nrl.navy.mil.itd.aic/files/pdfs/%28Uthus%20%26%20Aha%2C%20ICNLP-13%29%20Detecting%20Bot-Answerable%20Qns%20in%20Ubuntu%20Chat.pdf
NRL Publication Release Number: 
13-1231-2087
pub_tags: 
chat analysis
machine learning
automated question-answering
key_pub_tags: