LSTM CCG Parsing
Mike Lewis, Kenton Lee, Luke Zettlemoyer · 2016
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.