Papers with Code 아카이브
AMR Parsing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 75
Each AMR is a single rooted, directed graph. AMRs include PropBank semantic roles, within-sentence coreference, named entities and types, modality, negation, questions, quantities, and so on. See.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Core Semantic First: A Top-down Approach for AMR Parsing
Broad-Coverage Semantic Parsing as Transduction
Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
SemBleu: A Robust Metric for AMR Parsing Evaluation
AMR Parsing as Sequence-to-Graph Transduction
Automatic Accuracy Prediction for AMR Parsing
An Improved Approach for Semantic Graph Composition with CCG
An empirical evaluation of AMR parsing for legal documents
An AMR Aligner Tuned by Transition-based Parser
A Transition-based Algorithm for Unrestricted AMR Parsing
AMR Parsing as Graph Prediction with Latent Alignment
AMR Parsing using Stack-LSTMs
Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation
Robust Incremental Neural Semantic Graph Parsing
Addressing the Data Sparsity Issue in Neural AMR Parsing
An Incremental Parser for Abstract Meaning Representation
Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs
RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy
Robust Subgraph Generation Improves Abstract Meaning Representation Parsing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.