Generation of complex database queries and API calls from natural language utterances
This work provides a more accurate method for generating complex database queries and API calls from natural language, which is beneficial for developers and end-users interacting with databases and APIs.
This paper addresses the problem of generating complex database queries and API calls from natural language. The authors propose a method that transforms query generation into an intent classification and slot filling problem, achieving 92% exact match accuracy on a real-world dataset, significantly outperforming a state-of-the-art generative model's 60% accuracy.
Generating queries corresponding to natural language questions is a long standing problem. Traditional methods lack language flexibility, while newer sequence-to-sequence models require large amount of data. Schema-agnostic sequence-to-sequence models can be fine-tuned for a specific schema using a small dataset but these models have relatively low accuracy. We present a method that transforms the query generation problem into an intent classification and slot filling problem. This method can work using small datasets. For questions similar to the ones in the training dataset, it produces complex queries with high accuracy. For other questions, it can use a template-based approach or predict query pieces to construct the queries, still at a higher accuracy than sequence-to-sequence models. On a real-world dataset, a schema fine-tuned state-of-the-art generative model had 60\% exact match accuracy for the query generation task, while our method resulted in 92\% exact match accuracy.