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

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3547 - 3562 December 7-11, 2022 ©2022 Association for Computational Linguistics Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes Oren Sultan The Hebrew University of Jerusalem oren.sultan@mail.huji.ac.il Dafna Shahaf The Hebrew University of Jerusalem dshahaf@cs.huji.ac.il Abstract Analogy-making gives rise to reasoning, ab- straction, flexible categorization and counter- factual inference – abilities lacking in even the best AI systems today. Much research has sug- gested that analogies are key to non-brittle sys- tems that can adapt to new domains. Despite their importance, analogies received little atten- tion 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, de- scribing 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, achiev- ing 79% precision (analogy prevalence in data: 3%). Lastly, we demonstrate that our algorithm is robust to paraphrasing the input texts1. 1 Introduction The ability to find parallels across diverse domains and transfer ideas across them is one of the pinna- cles of human cognition. The analogous reasoning process allows us to abstract information, form flexible concepts and solve problems based on our previous experience (Minsky, 1988; Hofstadter and Sander, 2013; Holyoak, 1984) – abilities that cur- rent AI systems still lack. Many researchers have 1Data and code are available in our GitHub repository https://github.com/orensul/analogies_mining suggested that analogy-making is essential for engi- neering non-brittle AI that can robustly generalize and adapt to diverse domains (Mitchell, 2021b). Surprisingly, despite analogy’s important role in the way humans understand language, the problem of recognizing analogies has received relatively lit- tle attention in NLP. Most works have focused on SAT-type of analogies (“a to b is like c to d”), with recent works (Linzen, 2016; Ushio et al., 2021; Brown et al., 2020) showing that models still strug- gle with abstract, loosely defined relations. In this work, we focus on a different type of analogies: analogies between situations or pro- cesses. Here the input is two domains (e.g., heart and pump) and the goal is to map objects from the base domain to objects from the target domain. Im- portantly, the mapping should rely on a common relational structure rather than object attributes, making it challenging for NLP methods. The most influential work in this line of re- search is Structure Mapping Theory …

Content truncated to 500 words