Transition-Based Dependency Parsing with Stack Long Short-Term Memory
This work addresses the challenge of efficiently capturing parser state information for dependency parsing, which is incremental as it builds on existing neural network methods.
The paper tackles the problem of learning parser state representations in transition-based dependency parsing by introducing a stack LSTM, which combines a stack data structure with an LSTM to embed stack contents continuously, resulting in state-of-the-art parsing performance.
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.