Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching

  • Xiao Yang Pennsylvania State University
  • Madian Khabsa Apple
  • Miaosen Wang Google
  • Wei Wang Microsoft
  • Ahmed Hassan Awadallah Microsoft
  • Daniel Kifer Pennsylvania State University
  • C. Lee Giles Pennsylvania State University

Abstract

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REINFORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

Published
2019-07-17