Transition-Based Dependency Parsing using Perceptron Learner
This work addresses syntactic parsing for natural language processing, but it is incremental as it builds on existing transition-based methods with feature enhancements.
The paper tackles transition-based dependency parsing by enhancing a Perceptron Learner with additional features, resulting in improved performance over baseline arc-standard parsers and surpassing the UAS of MALT and LSTM parsers.
Syntactic parsing using dependency structures has become a standard technique in natural language processing with many different parsing models, in particular data-driven models that can be trained on syntactically annotated corpora. In this paper, we tackle transition-based dependency parsing using a Perceptron Learner. Our proposed model, which adds more relevant features to the Perceptron Learner, outperforms a baseline arc-standard parser. We beat the UAS of the MALT and LSTM parsers. We also give possible ways to address parsing of non-projective trees.