Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems
This addresses the challenge of controlling response quality for production NLG systems, but it is incremental as it focuses on grammaticality classification using existing methods.
The paper tackled the problem of ensuring grammatical correctness in production-ready natural language generation systems by proposing a generate, filter, and rank framework, and they released a dataset for the weather domain showing that high precision with reasonable recall can be achieved.
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.