Papers with Code 아카이브
nlg evaluation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Evaluate the generated text by NLG (Natural Language Generation) systems, like large language models
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Dialect-robust Evaluation of Generated Text
Towards a Unified Multi-Dimensional Evaluator for Text Generation
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics
The Authenticity Gap in Human Evaluation
A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lens of Semantic Similarity Rating
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications
Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets
Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding
Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
A Survey of Natural Language Generation
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Language Model Augmented Relevance Score
MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation
All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text
ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation
A Study of Automatic Metrics for the Evaluation of Natural Language Explanations
A Survey of Evaluation Metrics Used for NLG Systems
Evaluation of Text Generation: A Survey
Why We Need New Evaluation Metrics for NLG
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.