Abstract

Restricted non-monotonicity has been shown beneficial for the projective arc-eager dependency parser in previous research, as posterior decisions can repair mistakes made in previous states due to the lack of information. In this paper, we propose a novel, fully non-monotonic transition system based on the non-projective Covington algorithm. As a non-monotonic system requires exploration of erroneous actions during the training process, we develop several non-monotonic variants of the recently defined dynamic oracle for the Covington parser, based on tight approximations of the loss. Experiments on datasets from the CoNLL-X and CoNLL-XI shared tasks show that a non-monotonic dynamic oracle outperforms the monotonic version in the majority of languages.

Highlights

  • Greedy transition-based dependency parsers are widely used in different NLP tasks due to their speed and efficiency

  • We propose a non-monotonic transition system based on the non-projective Covington parser, together with a dynamic oracle to train it with erroneous examples that will need to be repaired

  • The accuracies obtained by the non-projective Covington parser with the three available oracles are presented in Table 3, in terms of Unlabeled (UAS) and Labeled Attachment Score (LAS)

Read more

Summary

Introduction

Greedy transition-based dependency parsers are widely used in different NLP tasks due to their speed and efficiency. They parse a sentence from left to right by greedily choosing the highestscoring transition to go from the current parser configuration or state to the next. McDonald and Nivre (2007) show that greedy transition-based parsers lose accuracy to error propagation: a transition erroneously chosen by the greedy parser can place it in an incorrect and unknown configuration, causing more mistakes in the rest of the transition sequence. Training with a dynamic oracle (Goldberg and Nivre, 2012) improves robustness in these situations, but in a monotonic transition system, erroneous decisions made in the past are permanent, even when the availability of further information in later states might be useful to correct them

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.