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 |
Papers
Showing 1–10 of 24 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Heterogeneous Dynamic Convolutions | Accuracy | 96.29 | — | Unverified |
| 2 | NeST-CCG + BERT | Accuracy | 96.25 | — | Unverified |
| 3 | CVT + Multi-task + Large | Accuracy | 96.1 | — | Unverified |
| 4 | BiLSTM-LAN | Accuracy | 94.7 | — | Unverified |
| 5 | Lewis et al. | Accuracy | 94.7 | — | Unverified |
| 6 | Vaswani et al. | Accuracy | 94.24 | — | Unverified |
| 7 | Low supervision | Accuracy | 93.26 | — | Unverified |
| 8 | Xu et al. | Accuracy | 93 | — | Unverified |