Abstract
Precisely assessing the progress in natural language generation (NLG) tasks is challenging, and human evaluation to establish a preference in a model’s output over another is often necessary.However, human evaluation is usually costly, difficult to reproduce, and non-reusable.In this paper, we propose a new and simple automatic evaluation method for NLG called Near-Negative Distinction (NND) that repurposes prior human annotations into NND tests.In an NND test, an NLG model must place a higher likelihood on a high-quality output candidate than on a near-negative candidate with a known error.Model performance is established by the number of NND tests a model passes, as well as the distribution over task-specific errors the model fails on.Through experiments on three NLG tasks (question generation, question answering, and summarization), we show that NND achieves a higher correlation with human judgments than standard NLG evaluation metrics. We then illustrate NND evaluation in four practical scenarios, for example performing fine-grain model analysis, or studying model training dynamics. Our findings suggest that NND can give a second life to human annotations and provide low-cost NLG evaluation.- Anthology ID:
- 2022.emnlp-main.135
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2094–2108
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.135
- DOI:
- 10.18653/v1/2022.emnlp-main.135
- Cite (ACL):
- Philippe Laban, Chien-Sheng Wu, Wenhao Liu, and Caiming Xiong. 2022. Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2094–2108, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets (Laban et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.emnlp-main.135.pdf