Skip to main navigation menu Skip to main content Skip to site footer

Easy-First Dependency Parsing with Hierarchical Tree LSTMs

Abstract

We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders. To demonstrate its effectiveness, we use the representation as the backbone of a greedy, bottom-up dependency parser, achieving very strong accuracies for English and Chinese, without relying on external word embeddings. The parser’s  implementation is available for download at the first author’s webpage.

PDF (presented at EMNLP 2016)