Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes
release_67ps44vxzveldgs6jjvdq5fwy4
by
Oren Sultan, Dafna Shahaf
2023
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.
In text/plain
format
Archived Files and Locations
application/pdf 1.6 MB
file_glg4rgpysfgctml2l2te6x6a4a
|
arxiv.org (repository) web.archive.org (webarchive) |
2210.12197v2
access all versions, variants, and formats of this works (eg, pre-prints)