Show simple item record

AuthorMalhas, Rana
AuthorTorki, Marwan
AuthorElsayed, Tamer
Available date2021-06-03T10:07:41Z
Publication Date2016
Publication NameSemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings
ResourceScopus
URIhttp://dx.doi.org/10.18653/v1/s16-1134
URIhttp://hdl.handle.net/10576/18555
AbstractResorting to community question answering (CQA) websites for finding answers has gained momentum in the past decade with the explosive rate at which social media has been proliferating. With many questions left unanswered on those websites, automatic and smart question answering systems have seen light. One of the main objectives of such systems is to harness the plethora of existing answered questions; hence transforming the problem to finding good answers to newly posed questions from similar previously-answered ones. As SemEval 2016 Task 3 "Community Question Answering" has focused on this problem, we have participated in the Arabic Subtask. Our system has adopted a supervised learning approach in which a learning-to-rank model is trained over data (questions and answers) extracted from Arabic CQA forums using word2vec features generated from that data. Our primary submission achieved a 29.7% improvement over the MAP score of the baseline. Post submission experiments were further conducted to integrate variations of the word2vec features to our system. Integrating covariance word embedding features has raised the the improvement over the baseline to 37.9%. 2016 Association for Computational Linguistics.
SponsorThis work was made possible by NPRP grant# NPRP 6-1377-1-257 from the Qatar National Research Fund (a member of Qatar Foundation).
Languageen
PublisherAssociation for Computational Linguistics (ACL)
SubjectSemantics
Websites
Community question answering
Learning to rank
Question answering systems
Social media
Subtask
Supervised learning approaches
Embeddings
TitleQU-IR at SemEval 2016 Task 3: Learning to rank on Arabic community question answering forums with word embedding
TypeConference Paper
Pagination866-871
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record