Transition-Based Dependency Parsing with Stack Long Short-Term Memory

TL;DR

This paper introduces a novel stack LSTM data structure for transition-based dependency parsing, enabling efficient state representation that captures look-ahead, parser history, and stack contents, resulting in improved parsing performance.

Contribution

The paper presents a new stack LSTM control structure that enhances transition-based dependency parsers by effectively modeling parser states with continuous embeddings.

Findings

Achieved state-of-the-art parsing accuracy.

Efficiently captures parser state components in a unified model.

Demonstrated effectiveness of stack LSTM in dependency parsing.

Abstract

We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks---the stack LSTM. Like the conventional stack data structures used in transition-based parsing, elements can be pushed to or popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. This lets us formulate an efficient parsing model that captures three facets of a parser's state: (i) unbounded look-ahead into the buffer of incoming words, (ii) the complete history of actions taken by the parser, and (iii) the complete contents of the stack of partially built tree fragments, including their internal structures. Standard backpropagation techniques are used for training and yield state-of-the-art parsing performance.