Semi-supervised question retrieval with gated convolutions
Name
Barzilay_Semi-supervied question.pdf
Size
784.4 KB
Format
Adobe PDF
Checksum (MD5)
9ca36e0b3260f1c57f6a0e6eda475459
Author(s)
Lei, Tao
Joshi, Hrishikesh S.
Barzilay, Regina
Jaakkola, Tommi S.
Date Issued
June 2016
Journal
NAACL 2016
Publisher
North American Chapter of the Association for Computational Linguistics
Citation
Lei, Tao, Hrishikesh Joshi Regina Barzilay and Tommi Jaakkola. "Semi-supervised Question Retrieval with Gated Convolutions." Paper presented at NAACL 2016 (San Diego, California, June 12 to June 17, 2016)
Version
Original manuscript
Abstract
Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations on similar questions are scarce and fragmented. We design a recurrent and convolutional model (gated convolution) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to
title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited
annotations. Our evaluation demonstrates that our model yields substantial gains over a standard IR baseline and various neural network architectures (including CNNs, LSTMs and GRUs).
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://dblp.dagstuhl.de/db/conf/naacl/naacl2016.html
