Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes

TL;DR

This paper presents an interpretable, scalable algorithm for automatically discovering analogies between complex procedural texts, significantly advancing NLP's ability to understand and relate diverse situations and processes.

Contribution

It introduces a novel method for extracting entities and relations from natural language texts to identify analogies, outperforming previous approaches in accuracy and scalability.

Findings

87% accuracy in identifying correct mappings between procedural texts

94% accuracy in analogy detection within cognitive-psychology stories

79% precision in extracting analogies from large datasets

Abstract

Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference -- abilities lacking in even the best AI systems today. Much research has suggested that analogies are key to non-brittle systems that can adapt to new domains. Despite their importance, analogies received little attention in the NLP community, with most research focusing on simple word analogies. Work that tackled more complex analogies relied heavily on manually constructed, hard-to-scale input representations. In this work, we explore a more realistic, challenging setup: our input is a pair of natural language procedural texts, describing a situation or a process (e.g., how the heart works/how a pump works). Our goal is to automatically extract entities and their relations from the text and find a mapping between the different domains based on relational similarity (e.g., blood is mapped to water). We develop an interpretable, scalable algorithm and demonstrate that it identifies the correct mappings 87% of the time for procedural texts and 94% for stories from cognitive-psychology literature. We show it can extract analogies from a large dataset of procedural texts, achieving 79% precision (analogy prevalence in data: 3%). Lastly, we demonstrate that our algorithm is robust to paraphrasing the input texts.