Accelerating innovation through analogy mining

Tom Hope, Joel Chan, Aniket Kittur, Dafna Shahaf

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


The availability of large idea repositories (e.g., patents) could significantly accelerate innovation and discovery by providing people inspiration from solutions to analogous problems. However, finding useful analogies in these large, messy, real-world repositories remains a persistent challenge for both humans and computers. Previous approaches include costly hand-created databases that do not scale, or machine-learning similarity metrics that struggle to account for structural similarity, which is central to analogy. In this paper1 we explore the viability and value of learning simple structural representations. Our approach combines crowdsourcing and recurrent neural networks to extract purpose and mechanism vector representations from product descriptions. We demonstrate that these learned vectors allow us to find analogies with higher precision and recall than traditional methods. In an ideation experiment, analogies retrieved by our models significantly increased people's likelihood of generating creative ideas.

Original languageAmerican English
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
PublisherInternational Joint Conferences on Artificial Intelligence
Number of pages5
ISBN (Electronic)9780999241127
StatePublished - 2018
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: 13 Jul 201819 Jul 2018

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823


Conference27th International Joint Conference on Artificial Intelligence, IJCAI 2018

Bibliographical note

Publisher Copyright:
© 2018 International Joint Conferences on Artificial Intelligence.All right reserved.


Dive into the research topics of 'Accelerating innovation through analogy mining'. Together they form a unique fingerprint.

Cite this