Latent Question Interpretation Through Variational Adaptation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 41
  • Download : 0
Most artificial neural network models for question-answering rely on complex attention mechanisms. These techniques demonstrate high performance on existing datasets; however, they are limited in their ability to capture natural language variability, and to generate diverse relevant answers. To address this limitation, we propose a model that learns multiple interpretations of a given question. This diversity is ensured by our interpretation policy module which automatically adapts the parameters of a question-answering model with respect to a discrete latent variable. This variable follows the distribution of interpretations learned by the interpretation policy through a semi-supervised variational inference framework. To boost the performance further, the resulting policy is fine-tuned using the rewards from the answer accuracy with a policy gradient. We demonstrate the relevance and efficiency of our model through a large panel of experiments. Qualitative results, in particular, underline the ability of the proposed architecture to discover multiple interpretations of a question. When tested using the Stanford Question Answering Dataset 1.1, our model outperforms the baseline methods in finding multiple and diverse answers. To assess our strategy from a human standpoint, we also conduct a large-scale user study. This study highlights the ability of our network to produce diverse and coherent answers compared to existing approaches. Our Pytorch implementation is available as open source.(1)
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2019-11
Language
English
Article Type
Article
Citation

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, v.27, no.11, pp.1713 - 1724

ISSN
2329-9290
DOI
10.1109/TASLP.2019.2929647
URI
http://hdl.handle.net/10203/265541
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0