mlsanityData to 14 Oct 2026

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

arXiv 2210.12197 ↗First posted 21 Oct 2022cs.CL cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

18 of 40 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  5. 2018Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehensioncited by 62
  6. 2021BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?cited by 56
  7. 2017Simulating Action Dynamics with Neural Process Networkscited by 53
  8. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  9. 2018Large-Scale QA-SRL Parsingcited by 45
  10. 2021Coreference Resolution without Span Representationscited by 45
  11. 2019Controlled Crowdsourcing for High-Quality QA-SRL Annotationcited by 34
  12. 2017Accelerating Innovation Through Analogy Miningcited by 32
6 more
  1. 2019Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Textcited by 31
  2. 2018Reasoning about Actions and State Changes by Injecting Commonsense Knowledgecited by 29
  3. 2016Issues in evaluating semantic spaces using word analogiescited by 27
  4. 2021QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositionscited by 16
  5. 2021Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrievalcited by 10
  6. 2020Inducing Alignment Structure with Gated Graph Attention Networks for Sentence Matchingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 10; 2025: 0; 2026: 2.

22 papers.

Sort:

By area:

  1. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  2. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  3. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  4. 2023In-Context Analogical Reasoning with Pre-Trained Language Modelscited by 22
  5. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogiescited by 13
  6. 2023Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abductioncited by 11
  7. 2023ARN: Analogical Reasoning on Narrativescited by 8
  8. 2024ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogiescited by 8
  9. 2024QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarizationcited by 8
  10. 2023Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruningcited by 7
  11. 2024Creativity in AI: Progresses and Challengescited by 7
  12. 2024Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluationcited by 5
10 more
  1. 2023FAME: Flexible, Scalable Analogy Mappings Enginecited by 3
  2. 2024Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?cited by 3
  3. 2024RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentationcited by 3
  4. 2023RelBERT: Embedding Relations with Language Modelscited by 1
  5. 2023On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Modelscited by 1
  6. 2024Past Meets Present: Creating Historical Analogy with Large Language Modelscited by 1
  7. 2024KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Promptingcited by 1
  8. 2026Effective QA-driven Annotation of Predicate-Argument Relations Across Languagescited by 1
  9. 2023Solving Hard Analogy Questions with Relation Embedding Chainscited by 0
  10. 2026FrameNet Semantic Role Classification by Analogycited by 0