Easy-First Dependency Parsing with Hierarchical Tree LSTMs

03/01/2016

∙

by   Eliyahu Kiperwasser, et al.

∙

0

∙

share

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 state-of-the-art 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.