Efficient Deployment of Conversational Natural Language Interfaces over Databases
This addresses the tedious and time-consuming data collection bottleneck for developers building conversational AI interfaces over databases, though it is an incremental improvement focused on data generation rather than model innovation.
The paper tackles the problem of needing large training datasets for natural language-to-query-language models by proposing a method to accelerate dataset collection, enabling the generation of conversational multi-term data that improved training efficiency and adaptability across SQL and SPARQL datasets.
Many users communicate with chatbots and AI assistants in order to help them with various tasks. A key component of the assistant is the ability to understand and answer a user's natural language questions for question-answering (QA). Because data can be usually stored in a structured manner, an essential step involves turning a natural language question into its corresponding query language. However, in order to train most natural language-to-query-language state-of-the-art models, a large amount of training data is needed first. In most domains, this data is not available and collecting such datasets for various domains can be tedious and time-consuming. In this work, we propose a novel method for accelerating the training dataset collection for developing the natural language-to-query-language machine learning models. Our system allows one to generate conversational multi-term data, where multiple turns define a dialogue session, enabling one to better utilize chatbot interfaces. We train two current state-of-the-art NL-to-QL models, on both an SQL and SPARQL-based datasets in order to showcase the adaptability and efficacy of our created data.