Grammar as a Foreign Language

TL;DR

This paper introduces a domain-agnostic, attention-enhanced sequence-to-sequence model for syntactic constituency parsing that achieves state-of-the-art accuracy, high data efficiency, and fast processing speeds.

Contribution

It demonstrates that a simple, attention-based seq2seq model can outperform complex parsers and be highly data-efficient for syntactic parsing tasks.

Findings

Achieves state-of-the-art results on standard datasets.

Matches performance of traditional parsers with limited human annotations.

Processes over a hundred sentences per second on CPU.

Abstract

Syntactic constituency parsing is a fundamental problem in natural language processing and has been the subject of intensive research and engineering for decades. As a result, the most accurate parsers are domain specific, complex, and inefficient. In this paper we show that the domain agnostic attention-enhanced sequence-to-sequence model achieves state-of-the-art results on the most widely used syntactic constituency parsing dataset, when trained on a large synthetic corpus that was annotated using existing parsers. It also matches the performance of standard parsers when trained only on a small human-annotated dataset, which shows that this model is highly data-efficient, in contrast to sequence-to-sequence models without the attention mechanism. Our parser is also fast, processing over a hundred sentences per second with an unoptimized CPU implementation.