Grammar as a Foreign Language
This addresses the problem of domain-specific, complex, and inefficient parsers in natural language processing, offering a domain-agnostic and data-efficient solution.
The paper tackled syntactic constituency parsing by showing that an attention-enhanced sequence-to-sequence model achieves state-of-the-art results on a widely used dataset when trained on a large synthetic corpus, and matches standard parser performance with a small human-annotated dataset, processing over a hundred sentences per second.
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.