Paper: Multimodal DBN for Predicting High-Quality Answers in cQA portals

ACL ID P13-2146
Title Multimodal DBN for Predicting High-Quality Answers in cQA portals
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

In this paper, we address the problem for predicting cQA answer quality as a clas- sification task. We propose a multimodal deep belief nets based approach that op- erates in two stages: First, the joint rep- resentation is learned by taking both tex- tual and non-textual features into a deep learning network. Then, the joint repre- sentation learned by the network is used as input features for a linear classifier. Ex- tensive experimental results conducted on two cQA datasets demonstrate the effec- tiveness of our proposed approach.