Grammar as a Foreign Language
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2014
- DOI:
- 10.48550/arXiv.1412.7449
- arXiv:
- arXiv:1412.7449
- Bibcode:
- 2014arXiv1412.7449V
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Machine Learning;
- Statistics - Machine Learning