Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States

Ashish Vaswani, Kenji Sagae


Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach produces the highest accuracy for transition-based dependency parsing in English.


  • There are currently no refbacks.

Copyright (c) 2016 Association for Computational Linguistics

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.