Hand in Glove: Deep Feature Fusion Network Architectures for Answer Quality Prediction in Community Question Answering

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1429–1440, Osaka, Japan, December 11-17 2016. Hand in Glove: Deep Feature Fusion Network Architectures for Answer Quality Prediction in Community Question Answering Sai Praneeth Suggu⋆ Kushwanth N. Goutham⋆ Manoj K. Chinnakotla† Manish Shrivastava⋆ ⋆IIIT Hyderabad, India {suggusai.praneeth,kushwanth.naga}@research.iiit.ac.in m.shrivastava@iiit.ac.in †Microsoft, India manojc@microsoft.com Abstract Community Question Answering (cQA) forums have become a popular medium for soliciting answers to specific user questions from experts and experienced users in a given topic. However, for a given question, users sometimes have to sift through a large number of low-quality or irrelevant answers to find out the answer which satisfies their information need. To alleviate this, the problem of Answer Quality Prediction (AQP) aims to predict the quality of an answer posted in response to a forum question. Current AQP systems either learn models using - a) various hand-crafted features (HCF) or b) Deep Learning (DL) techniques which automatically learn the feature representations. In this paper, we propose a novel approach for AQP known as - “Deep Feature Fusion Network (DFFN)” which combines the advantages of both hand-crafted features and deep learning based systems. Given a question-answer pair along with its metadata, a DFFN architecture indepen- dently - a) learns features using the Deep Neural Network (DNN) and b) computes hand-crafted features leveraging various external resources and then combines them using a fully connected neural network trained to predict the quality of the given answer. DFFN is an end-end differen- tiable model and trained as a single system. We propose two different DFFN architectures which vary mainly in the way they model the input question/answer pair - a) DFFN-CNN which uses a Convolutional Neural Network (CNN) and b) DFFN-BLNA which uses a Bi-directional LSTM with Neural Attention (BLNA). Both these proposed variants of DFFN (DFFN-CNN and DFFN- BLNA) achieve state-of-the-art performance on the standard SemEval-2015 and SemEval-2016 benchmark datasets and outperforms baseline approaches which individually employ either HCF or DL based techniques alone. 1 Introduction Community Question Answering (cQA) forums (such as Yahoo! Answers, Stack Overflow, etc.) have become a popular medium for many internet users to get precise answers or opinions to their questions from experts or other experienced users in the topic. Such forums are usually open, allowing any user to respond to a given question. As a result, for a question posed by the user, the quality of response often varies a lot - ranging from highly precise and detailed answers given by authentic users to highly imprecise or non-comprehensible one-word or single line answers posted by spammy and other non- serious users. This severely hampers the effectiveness of cQA forums since users will have to sift through a large number of irrelevant posts to find the answer which satisfies their information need. To alleviate this problem, cQA forums often include feedback mechanisms such as votes, ratings etc. for evaluating the quality of answers and users. Such user feedback could also be used as signals for ranking multiple answers …

Content truncated to 500 words