Skip to content

Latest commit

 

History

History
28 lines (21 loc) · 1.64 KB

ccg_supertagging.md

File metadata and controls

28 lines (21 loc) · 1.64 KB

CCG supertagging

Combinatory Categorical Grammar (CCG; Steedman, 2000) is a highly lexicalized formalism. The standard parsing model of Clark and Curran (2007) uses over 400 lexical categories (or supertags), compared to about 50 part-of-speech tags for typical parsers.

Example:

Vinken , 61 years old
N , N/N N (S[adj]\ NP)\ NP

CCGBank

The CCGBank is a corpus of CCG derivations and dependency structures extracted from the Penn Treebank by Hockenmaier and Steedman (2007). Sections 2-21 are used for training, section 00 for development, and section 23 as in-domain test set. Performance is only calculated on the 425 most frequent labels. Models are evaluated based on accuracy.

Model Accuracy Paper / Source
Clark et al. (2018) 96.1 Semi-Supervised Sequence Modeling with Cross-View Training
Lewis et al. (2016) 94.7 LSTM CCG Parsing
Vaswani et al. (2016) 94.24 Supertagging with LSTMs
Low supervision (Søgaard and Goldberg, 2016) 93.26 Deep multi-task learning with low level tasks supervised at lower layers
Xu et al. (2015) 93.00 CCG Supertagging with a Recurrent Neural Network

Go back to the README