Dependency Parsing with LSTMs: An Empirical Evaluation
Computation and Language
2016-07-01 v2 Machine Learning
Neural and Evolutionary Computing
Abstract
We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units. This extends the feedforward neural network parser of Chen and Manning (2014) and enables modelling of entire sequences of shift/reduce transition decisions. On the Google Web Treebank, our LSTM parser is competitive with the best feedforward parser on overall accuracy and notably achieves more than 3% improvement for long-range dependencies, which has proved difficult for previous transition-based parsers due to error propagation and limited context information. Our findings additionally suggest that dropout regularisation on the embedding layer is crucial to improve the LSTM's generalisation.
Cite
@article{arxiv.1604.06529,
title = {Dependency Parsing with LSTMs: An Empirical Evaluation},
author = {Adhiguna Kuncoro and Yuichiro Sawai and Kevin Duh and Yuji Matsumoto},
journal= {arXiv preprint arXiv:1604.06529},
year = {2016}
}
Comments
7 pages, 4 figures