On the Benefit of Incorporating External Features in a Neural Architecture for Answer Sentence Selection

Incorporating conventional, unsupervised features into a neural architecture has the potential to improve modeling effectiveness, but this aspect is often overlooked in the research of deep learning models for information retrieval. We investigate this incorporation in the context of answer sentence selection, and show that combining a set of query matching, readability, and query focus features into a simple convolutional neural network can lead to markedly increased effectiveness. Our results on two standard question-answering datasets show the effectiveness of the combined model.

[1]  Tapas Kanungo,et al.  Predicting the readability of short web summaries , 2009, WSDM '09.

[2]  Alistair Moffat,et al.  Improvements that don't add up: ad-hoc retrieval results since 1998 , 2009, CIKM.

[3]  Yi Yang,et al.  WikiQA: A Challenge Dataset for Open-Domain Question Answering , 2015, EMNLP.

[4]  Jimmy J. Lin,et al.  Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement , 2016, NAACL.

[5]  W. Bruce Croft,et al.  Beyond Factoid QA: Effective Methods for Non-factoid Answer Sentence Retrieval , 2016, ECIR.

[6]  Alessandro Moschitti,et al.  Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks , 2015, SIGIR.

[7]  Daniele Bonadiman,et al.  Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking , 2016, NAACL.

[8]  Noah A. Smith,et al.  What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA , 2007, EMNLP.

[9]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[10]  Jaime G. Carbonell,et al.  Rank learning for factoid question answering with linguistic and semantic constraints , 2010, CIKM.

[11]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[12]  Di Wang,et al.  A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering , 2015, ACL.

[13]  Lei Yu,et al.  Deep Learning for Answer Sentence Selection , 2014, ArXiv.

[14]  Bowen Zhou,et al.  ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs , 2015, TACL.

[15]  Zhiguo Wang,et al.  Sentence Similarity Learning by Lexical Decomposition and Composition , 2016, COLING.

[16]  W. Bruce Croft,et al.  aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model , 2016, CIKM.

[17]  SurdeanuMihai,et al.  Learning to rank answers to non-factoid questions from web collections , 2011 .

[18]  Ming-Wei Chang,et al.  Open Domain Question Answering via Semantic Enrichment , 2015, WWW.

[19]  Jimmy J. Lin,et al.  Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks , 2016, CIKM.

[20]  W. Bruce Croft,et al.  Retrieving Passages and Finding Answers , 2014, ADCS '14.