Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems

Ashwini Challa, Kartikeya Upasani, Anusha Balakrishnan, Rajen Subba


Abstract
Neural approaches to Natural Language Generation (NLG) have been promising for goal-oriented dialogue. One of the challenges of productionizing these approaches, however, is the ability to control response quality, and ensure that generated responses are acceptable. We propose the use of a generate, filter, and rank framework, in which candidate responses are first filtered to eliminate unacceptable responses, and then ranked to select the best response. While acceptability includes grammatical correctness and semantic correctness, we focus only on grammaticality classification in this paper, and show that existing datasets for grammatical error correction don’t correctly capture the distribution of errors that data-driven generators are likely to make. We release a grammatical classification and semantic correctness classification dataset for the weather domain that consists of responses generated by 3 data-driven NLG systems. We then explore two supervised learning approaches (CNNs and GBDTs) for classifying grammaticality. Our experiments show that grammaticality classification is very sensitive to the distribution of errors in the data, and that these distributions vary significantly with both the source of the response as well as the domain. We show that it’s possible to achieve high precision with reasonable recall on our dataset.
Anthology ID:
N19-2027
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Anastassia Loukina, Michelle Morales, Rohit Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
214–225
Language:
URL:
https://aclanthology.org/N19-2027
DOI:
10.18653/v1/N19-2027
Bibkey:
Cite (ACL):
Ashwini Challa, Kartikeya Upasani, Anusha Balakrishnan, and Rajen Subba. 2019. Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 214–225, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems (Challa et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-2027.pdf
Code
 facebookresearch/momi