English

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets

Computation and Language 2022-11-10 v2

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.

Keywords

Cite

@article{arxiv.2205.06871,
  title  = {Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets},
  author = {Philippe Laban and Chien-Sheng Wu and Wenhao Liu and Caiming Xiong},
  journal= {arXiv preprint arXiv:2205.06871},
  year   = {2022}
}

Comments

EMNLP 2022 - Long Paper