ABSTRACT
In recent years, neural networks have been applied to many text processing problems. One example is learning a similarity function between pairs of text, which has applications to paraphrase extraction, plagiarism detection, question answering, and ad hoc retrieval. Within the information retrieval community, the convolutional neural network model proposed by Severyn and Moschitti in a SIGIR 2015 paper has gained prominence. This paper focuses on the problem of answer selection for question answering: we attempt to replicate the results of Severyn and Moschitti using their open-source code as well as to reproduce their results via a de novo (i.e., from scratch) implementation using a completely different deep learning toolkit. Our de novo implementation is instructive in ascertaining whether reported results generalize across toolkits, each of which have their idiosyncrasies. We were able to successfully replicate and reproduce the reported results of Severyn and Moschitti, albeit with minor differences in effectiveness, but affirming the overall design of their model. Additional ablation experiments break down the components of the model to show their contributions to overall effectiveness. Interestingly, we find that removing one component actually increases effectiveness and that a simplified model with only four word overlap features performs surprisingly well, even better than convolution feature maps alone.
- ACL 2017. Question Answering (State of the art). http://www.aclweb.org/aclwiki/index.php?title=Question_Answering_(State_of_the_art). Accessed: 2017-05-01.Google Scholar
- Jaime Arguello, Matt Crane, Fernando Diaz, Jimmy Lin, and Andrew Trotman. 2015. Report on the SIGIR 2015 Workshop on Reproducibility, Inexplicability, and Generalizability of Results (RIGOR). SIGIR Forum, Vol. 49, 2 (2015), 107--116.Google ScholarDigital Library
- Jane Bromley, Isabelle Guyon, Yann LeCun, Eduard Säckinger, and Roopak Shah. 1993. Signature Verification Using a "Siamese" Time Delay Neural Network NIPS. 737--744.Google Scholar
- Abdessamad Echihabi and Daniel Marcu. 2003. A Noisy-Channel Approach to Question Answering. In ACL. 16--23. Google ScholarDigital Library
- Jiafeng Guo, Yixing Fan, Qingyao Ai, and W. Bruce Croft. 2016. A Deep Relevance Matching Model for Ad-hoc Retrieval CIKM. 55--64.Google Scholar
- Hua He, Kevin Gimpel, and Jimmy Lin. 2015. Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks EMNLP. 1576--1586.Google Scholar
- Hua He and Jimmy Lin. 2016. Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement NAACL. 937--948.Google Scholar
- Hua He, John Wieting, Kevin Gimpel, Jinfeng Rao, and Jimmy Lin. 2016. UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement SemEval. 662--667.Google Scholar
- Michael Heilman and Noah A. Smith. 2010. Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions. In HLT-NAACL. 1011--1019.Google ScholarDigital Library
- Jimmy Lin, Matt Crane, Andrew Trotman, Jamie Callan, Ishan Chattopadhyaya, John Foley, Grant Ingersoll, Craig Macdonald, and Sebastiano Vigna. 2016. Toward Reproducible Baselines: The Open-Source IR Reproducibility Challenge ECIR. 408--420.Google Scholar
- Yishu Miao, Lei Yu, and Phil Blunsom. 2015. Neural Variational Inference for Text Processing. arXiv:1511.06038.Google Scholar
- Jinfeng Rao, Hua He, and Jimmy Lin. 2016. Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks CIKM. 1913--1916.Google Scholar
- Jinfeng Rao, Jimmy Lin, and Miles Efron. 2015. Reproducible Experiments on Lexical and Temporal Feedback for Tweet Search ECIR. 755--767.Google Scholar
- Aliaksei Severyn and Alessandro Moschitti. 2015. Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks SIGIR. 373--382.Google Scholar
- Stefanie Tellex, Boris Katz, Jimmy Lin, Gregory Marton, and Aaron Fernandes. 2003. Quantitative Evaluation of Passage Retrieval Algorithms for Question Answering SIGIR. 41--47.Google Scholar
- Ellen M. Voorhees. 2002. Overview of the TREC 2002 Question Answering Track TREC.Google Scholar
- Di Wang and Eric Nyberg. 2015. A Long Short-Term Memory Model for Answer Sentence Selection in Question Answering ACL. 707--712.Google Scholar
- Mengqiu Wang and Christopher D. Manning. 2010. Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering. In COLING. 1164--1172.Google Scholar
- Mengqiu Wang, Noah A. Smith, and Teruko Mitamura. 2007. What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA EMNLP-CoNLL. 22--32.Google Scholar
- Xuchen Yao, Benjamin Van Durme, Chris Callison-Burch, and Peter Clark. 2013. Answer Extraction as Sequence Tagging with Tree Edit Distance HLT-NAACL. 858--867.Google Scholar
- Wen-tau Yih, Ming-Wei Chang, Christopher Meek, and Andrzej Pastusiak. 2013. Question Answering Using Enhanced Lexical Semantic Models ACL. 1744--1753.Google Scholar
Index Terms
- Experiments with Convolutional Neural Network Models for Answer Selection
Recommendations
Knowledge-aware Attentive Neural Network for Ranking Question Answer Pairs
SIGIR '18: The 41st International ACM SIGIR Conference on Research & Development in Information RetrievalRanking question answer pairs has attracted increasing attention recently due to its broad applications such as information retrieval and question answering (QA). Significant progresses have been made by deep neural networks. However, background ...
Recurrent convolutional neural network for answer selection in community question answering
AbstractIn this paper, we propose a recurrent convolutional neural network (RCNN) for answer selection in community question answering (CQA). It combines convolutional neural network (CNN) with recurrent neural network (RNN) to capture both ...
Human question answering performance using an interactive document retrieval system
IIIX '12: Proceedings of the 4th Information Interaction in Context SymposiumEvery day, people answer their questions by using document retrieval systems. Compared to document retrieval systems, question answering (QA) systems aim to speed the rate at which users find answers by retrieving answers rather than documents. To ...
Comments