Incremental Parsing with Minimal Features Using Bi-Directional LSTM

Abstract

Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting important global context. To further reduce feature engineering to the bare minimum, we use bi-directional LSTM sentence representations to model a parser state with only three sentence positions, which automatically identifies important aspects of the entire sentence. This model achieves state-of-the-art results among greedy dependency parsers for English. We also introduce a novel transition system for constituency parsing which does not require binarization, and together with the above architecture, achieves state-of-the-art results among greedy parsers for both English and Chinese.

arXiv commentPre-print of paper appearing in ACL 2016

References in corpus (5)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
• Structured Training for Neural Network Transition-Based Parsing

Cited by in corpus (3)

• A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters
• Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank
• Water Supply Prediction Based on Initialized Attention Residual Network