Sequence Labeling and Transduction with Output-Adjusted Actor-Critic Training of RNNs

  • Author / Creator
    Najafi, Saeed
  • Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an attractive alternative to CRFs for sequence labeling. To do so, we address one of the RNN’s most prominent shortcomings, the fact that it is not exposed to its own errors with the maximum-likelihood training. We frame the prediction of the output sequence as a sequential decision-making process, where the RNN takes a series of actions without being conditioned on the ground-truth labels. We then train the network with an output-adjusted actor-critic algorithm (AC-RNN). We comprehensively compare this strategy with maximum-likelihood training for both RNNs and CRFs on three structured-output tasks. The proposed AC-RNN efficiently matches the performance of the CRF on NER and CCG tagging, and outperforms it on machine transliteration. We show that the output-adjusted actor-critic training is significantly better than other techniques for addressing RNN’s exposure bias, such as Scheduled Sampling, and Self-Critical policy training.

  • Subjects / Keywords
  • Graduation date
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.