Investigating multi-task learning in semantic parsing

Current research in semantic parsing suffers from lack of annotated data, which is hard to acquire. In this project, we aim at tackling the problem of converting natural language utterances to SQL language (Text-to-SQL) on complex databases in a low-resource environment. More specifically, we focus on the research of how multi-task learning (MTL) can help in this task. We will first identify the related natural language processing (NLP) tasks that can contribute to improving the performance of semantic parsing. Additionally, we will explore the methods of bridging multiple NLP tasks, and justify by empirical results what are the better methods for knowledge transferring. We want to push the state-of-the-art on the existing benchmarks on semantic parsing, and eventually, we hope this project could result in a successful product. The product will then help RBC reduce the analysts’ workload so that they can provide better services. Furthermore, the potential publications in this domain would also contribute to the overall research leadership that Canada maintains in AI.

Intern: 
Chenyang Huang
Faculty Supervisor: 
Osmar Zaiane;Lili Mou
Province: 
Alberta
Partner: 
Partner University: 
Discipline: 
Program: