LSTM CCG Parsing
Mike Lewisa b, Kenton Leea b, Luke Zettlemoyera b
- aComputer Science & Engineering University of Washington Seattle , WA 98195
- bUniversity of Washington
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
We demonstrate that a state-of-the-art parser can be built using only a lexical tagging model and a deterministic grammar, with no explicit model of bi-lexical dependencies.Instead, all dependencies are implicitly encoded in an LSTM supertagger that assigns CCG lexical categories.The parser significantly outperforms all previously published CCG results, supports efficient and optimal A * decoding, and benefits substantially from semisupervised tri-training.We give a detailed analysis, demonstrating that the parser can recover long-range dependencies with high accuracy and that the semi-supervised learning enables significant accuracy gains.By running the LSTM on a GPU, we are able to parse over 2600 sentences per second while improving state-of-the-art accuracy by 1.1 F1 in domain and up to 4.5 F1 out of domain.
TL;DRThis work demonstrates that a state-of-the-art parser can be built using only a lexical tagging model and a deterministic grammar, with no explicit model of bi-lexical dependencies, and can recover long-range dependencies with high accuracy. (Semantic Scholar)