Together we stand: Siamese Networks for Similar Question Retrieval

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 378–387, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Together We Stand: Siamese Networks for Similar Question Retrieval Arpita Das1 Harish Yenala1 Manoj Chinnakotla2,1 Manish Shrivastava1 1IIIT Hyderabad, Hyderabad, India {arpita.das,harish.yenala}@research.iiit.ac.in m.shrivastava@iiit.ac.in 2Microsoft, Hyderabad, India manojc@microsoft.com Abstract Community Question Answering (cQA) services like Yahoo! Answers1, Baidu Zhidao2, Quora3, StackOverflow4 etc. provide a platform for interaction with experts and help users to obtain precise and accurate answers to their questions. The time lag between the user posting a question and receiving its answer could be reduced by retrieving similar historic questions from the cQA archives. The main challenge in this task is the “lexico- syntactic” gap between the current and the previous questions. In this paper, we pro- pose a novel approach called “Siamese Convolutional Neural Network for cQA (SCQA)” to find the semantic similarity between the current and the archived ques- tions. SCQA consist of twin convolu- tional neural networks with shared param- eters and a contrastive loss function join- ing them. SCQA learns the similarity metric for question-question pairs by leveraging the question-answer pairs available in cQA fo- rum archives. The model projects semanti- cally similar question pairs nearer to each other and dissimilar question pairs far- ther away from each other in the seman- tic space. Experiments on large scale real- life “Yahoo! Answers” dataset reveals that SCQA outperforms current state-of-the- art approaches based on translation mod- els, topic models and deep neural network 1https://answers.yahoo.com/ 2http://zhidao.baidu.com/ 3http://www.quora.com/ 4http://stackoverflow.com/ based models which use non-shared pa- rameters. 1 Introduction The cQA forums have emerged as popular and effective means of information exchange on the Web. Users post queries in these forums and re- ceive precise and compact answers in stead of a list of documents. Unlike in Web search, opinion based queries are also answered here by experts and users based on their personal experiences. The question and answers are also enhanced with rich metadata like categories, subcategories, user ex- pert level, user votes to answers etc. One of the serious concerns in cQA is “question-starvation” (Li and King, 2010) where a question does not get immediate answer from any user. When this happens, the question may take several hours and sometimes days to get sat- isfactory answers or may not get answered at all. This delay in response may be avoided by re- trieving semantically related questions from the cQA archives. If a similar question is found in the database of previous questions, then the corre- sponding best answer can be provided without any delay. However, the major challenge associated with retrieval of similar questions is the lexico- syntactic gap between them. Two questions may mean the same thing but they may differ lexically and syntactically. For example the queries “Why are yawns contagious?” and “Why do we yawn when we see somebody else yawning?” convey the same meaning but differ drastically from each other in terms of words and syntax. Several techniques have …

Content truncated to 500 words