Supervised attention for answer selection in community question answering
Answer selection is an important task in Community Question Answering (CQA). In recent years, attention-based neural networks have been extensively studied in various natural language processing problems, including question answering. This paper explores matchLSTM for answer selection in CQA. A lexi...
Saved in:
Published in | IAES International Journal of Artificial Intelligence Vol. 9; no. 2; p. 203 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Yogyakarta
IAES Institute of Advanced Engineering and Science
01.06.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Answer selection is an important task in Community Question Answering (CQA). In recent years, attention-based neural networks have been extensively studied in various natural language processing problems, including question answering. This paper explores matchLSTM for answer selection in CQA. A lexical gap in CQA is more challenging as questions and answers typical contain multiple sentences, irrelevant information, and noisy expressions. In our investigation, word-by-word attention in the original model does not work well on social question-answer pairs. We propose integrating supervised attention into matchLSTM . Specifically, we leverage lexical-semantic from external to guide the learning of attention weights for question-answer pairs. The proposed model learns more meaningful attention that allows performing better than the basic model. Our performance is among the top on SemEval datasets. |
---|---|
ISSN: | 2089-4872 2252-8938 2089-4872 |
DOI: | 10.11591/ijai.v9.i2.pp203-211 |