Semi-supervised question retrieval with gated convolutions
Author(s)Lei, Tao; Joshi, Hrishikesh S.; Barzilay, Regina; Jaakkola, Tommi S.
MetadataShow full item record
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).
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Department of Mathematics
North American Chapter of the Association for Computational Linguistics
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)