Natural Language Commanding via Program Synthesis

TL;DR

This paper introduces Semantic Interpreter, an AI system that uses large language models and a specialized domain language to accurately interpret and execute natural language commands in Microsoft Office applications, especially PowerPoint.

Contribution

It proposes the Office Domain Specific Language (ODSL) and an analysis-retrieval prompt method for translating natural language into application-specific programs.

Findings

Effective translation of natural language to ODSL programs

Successful execution of commands in PowerPoint via program synthesis

Enhanced understanding of user intent in productivity software

Abstract

We present Semantic Interpreter, a natural language-friendly AI system for productivity software such as Microsoft Office that leverages large language models (LLMs) to execute user intent across application features. While LLMs are excellent at understanding user intent expressed as natural language, they are not sufficient for fulfilling application-specific user intent that requires more than text-to-text transformations. We therefore introduce the Office Domain Specific Language (ODSL), a concise, high-level language specialized for performing actions in and interacting with entities in Office applications. Semantic Interpreter leverages an Analysis-Retrieval prompt construction method with LLMs for program synthesis, translating natural language user utterances to ODSL programs that can be transpiled to application APIs and then executed. We focus our discussion primarily on a research exploration for Microsoft PowerPoint.