Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Adversarial reading networks for machine comprehension
Quentin Grail, Julien Perez
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Machine reading has recently shown remarkable progress thanks to differentiable
reasoning models. In this context, End-to-End trainable Memory Networks
(MemN2N) have demonstrated promising performance on simple natural language
based reasoning tasks such as factual reasoning and basic deduction. However,
the task of machine comprehension is currently bounded to a supervised setting
and available question answering dataset. In this paper we explore the paradigm
of adversarial learning and self-play for the task of machine reading comprehension.
Inspired by the successful propositions in the domain of game learning, we
present a novel approach of training for this task that is based on the definition
of a coupled attention-based memory model. On one hand, a reader network is
in charge of finding answers regarding a passage of text and a question. On the
other hand, a narrator network is in charge of obfuscating spans of text in order
to minimize the probability of success of the reader. We experimented the model
on several question-answering corpora. The proposed learning paradigm and associated
models present encouraging results.
Keywords:machine reading, adversarial training
Enter your feedback below and we'll get back to you as soon as possible.