NLP4Prog

Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based Techniques

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing

Explaining Large Language Model-based Semantic Parsers

Language and Code

We seek to build natural language interfaces that allow humans to communicate with computers/machines easily. This requires modeling natural language, programming language, and their interplay. Applications of this research include semantic parsing and general-purpose code generation.

Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors

Learning Structural Edits via Incremental Tree Transformations

An Imitation Game for Learning Semantic Parsers from User Interaction

CoaCor: Code annotation for code retrieval with reinforcement learning

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study