Unifying Human and Statistical Evaluation for Natural Language Generation

Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang


Abstract
How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set. On the other hand, statistical evaluation (i.e., perplexity) captures diversity but not quality, as models that occasionally emit low quality samples would be insufficiently penalized. In this paper, we propose a unified framework which evaluates both diversity and quality, based on the optimal error rate of predicting whether a sentence is human- or machine-generated. We demonstrate that this error rate can be efficiently estimated by combining human and statistical evaluation, using an evaluation metric which we call HUSE. On summarization and chit-chat dialogue, we show that (i) HUSE detects diversity defects which fool pure human evaluation and that (ii) techniques such as annealing for improving quality actually decrease HUSE due to decreased diversity.
Anthology ID:
N19-1169
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1689–1701
Language:
URL:
https://aclanthology.org/N19-1169
DOI:
10.18653/v1/N19-1169
Bibkey:
Cite (ACL):
Tatsunori B. Hashimoto, Hugh Zhang, and Percy Liang. 2019. Unifying Human and Statistical Evaluation for Natural Language Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1689–1701, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Unifying Human and Statistical Evaluation for Natural Language Generation (Hashimoto et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1169.pdf
Code
 worksheets/0x88644b5e +  additional community code