Reasoning about Procedures with Natural Language Processing: A Tutorial

TL;DR

This tutorial reviews recent advances in natural language processing for understanding, representing, and reasoning about procedures, highlighting methods for collection, reasoning frameworks, and real-world applications.

Contribution

It provides a comprehensive overview of procedural reasoning in NLP, covering collection, representation, reasoning approaches, and practical scenarios, serving as a guide for future research.

Findings

Summarizes approaches to collect procedures via annotation and web extraction.

Discusses various reasoning and representation methods for procedures.

Highlights real-world applications of procedural knowledge in NLP.

Abstract

This tutorial provides a comprehensive and in-depth view of the research on procedures, primarily in Natural Language Processing. A procedure is a sequence of steps intended to achieve some goal. Understanding procedures in natural language has a long history, with recent breakthroughs made possible by advances in technology. First, we discuss established approaches to collect procedures, by human annotation or extraction from web resources. Then, we examine different angles from which procedures can be reasoned about, as well as ways to represent them. Finally, we enumerate scenarios where procedural knowledge can be applied to the real world.