Papers with Code 아카이브
CCG Supertagging
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 8
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 |
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Something Old, Something New: Grammar-based CCG Parsing with Transformer Models
Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks
Hierarchically-Refined Label Attention Network for Sequence Labeling
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
Semi-Supervised Sequence Modeling with Cross-View Training
Targeted Syntactic Evaluation of Language Models
A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models
Exploring the Syntactic Abilities of RNNs with Multi-task Learning
An Empirical Exploration of Skip Connections for Sequential Tagging
Keystroke dynamics as signal for shallow syntactic parsing
A Dynamic Window Neural Network for CCG Supertagging
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.