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- Anthology ID:
- 2022.emnlp-main.232
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3547–3562
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2022.emnlp-main.232/
- DOI:
- 10.18653/v1/2022.emnlp-main.232
- Cite (ACL):
- Oren Sultan and Dafna Shahaf. 2022. Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3547–3562, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes (Sultan & Shahaf, EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2022.emnlp-main.232.pdf