Easy-First Dependency Parsing with Hierarchical Tree LSTMs

TL;DR

This paper introduces a recursive vector representation of parse trees using hierarchical Tree LSTMs, enabling a greedy bottom-up dependency parser that achieves state-of-the-art accuracy without external word embeddings.

Contribution

It presents a novel hierarchical Tree LSTM-based tree representation and demonstrates its effectiveness in a dependency parser surpassing previous accuracy records.

Findings

Achieved state-of-the-art accuracy for English and Chinese dependency parsing

The parser does not rely on external word embeddings

The implementation is publicly available

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 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.