Generating Well-Formed Answers by Machine Reading with Stochastic Selector Networks

  • Bin Bi Alibaba
  • Chen Wu Alibaba
  • Ming Yan Alibaba
  • Wei Wang Alibaba
  • Jiangnan Xia Alibaba
  • Chenliang Li Alibaba

Abstract

Question answering (QA) based on machine reading comprehension has been a recent surge in popularity, yet most work has focused on extractive methods. We instead address a more challenging QA problem of generating a well-formed answer by reading and summarizing the paragraph for a given question.

For the generative QA task, we introduce a new neural architecture, LatentQA, in which a novel stochastic selector network composes a well-formed answer with words selected from the question, the paragraph and the global vocabulary, based on a sequence of discrete latent variables. Bayesian inference for the latent variables is performed to train the LatentQA model. The experiments on public datasets of natural answer generation confirm the effectiveness of LatentQA in generating high-quality well-formed answers.

Published
2020-04-03
Section
AAAI Technical Track: Natural Language Processing