Programming by Example and Text-to-Code Translation for Conversational Code Generation

TL;DR

This paper introduces MPaTHS, a modular system that combines Programming by Example and text-to-code translation to improve natural language program synthesis in dialogue systems.

Contribution

The paper presents a novel modular framework that integrates two advanced program synthesis techniques for more flexible dialogue system responses.

Findings

Demonstrates MPaTHS's ability to synthesize complex programs from natural language.

Shows improved flexibility in dialogue response generation.

Provides a new program representation suitable for task-oriented dialogue.

Abstract

Dialogue systems is an increasingly popular task of natural language processing. However, the dialogue paths tend to be deterministic, restricted to the system rails, regardless of the given request or input text. Recent advances in program synthesis have led to systems which can synthesize programs from very general search spaces, e.g. Programming by Example, and to systems with very accessible interfaces for writing programs, e.g. text-to-code translation, but have not achieved both of these qualities in the same system. We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs. We present a program representation that allows our method to be applied to the problem of task-oriented dialogue. Finally, we demo MPaTHS using our program representation.