Scaling Up Innovation through Analogy Mining ERC SIAM, grant no. 852686

Many world-changing breakthroughs in science and technology were enabled by analogical transfer, as ideas from one domain were used to solve a problem in another. Observing water led the Greek philosopher Chrysippus to speculate that sound was a wave phenomenon; an analogy to twisting a cardboard box allowed the Wright brothers to design a steerable aircraft.

Despite its value for innovation, very little progress has been made towards automating the process of analogy-finding in real-world settings, and the problem has maintained a longstanding status as a “holy grail" in artificial intelligence.

The goal of this project is to tackle head-on this important problem and develop principled tools for automatically discovering analogies in large, unstructured, natural-language datasets such as patents and scientific papers. Such tools could revolutionize a variety of fields, allowing scientists and inventors to retrieve useful content based on deep structural similarity rather than simple keywords.

In particular, this project explores the multiple roles AI and machine learning can play in the analogical innovation pipeline. In ideation experiments, analogies retrieved by our models significantly increased people's likelihood of generating creative ideas.

Ronen Tamari, Chen Shani, Tom Hope, Miriam RL Petruck, Omri Abend, and Dafna Shahaf, Language (re)modelling: Towards embodied language understanding
Association for Computational Linguistics (ACL), 2020


Ronen Tamari, Gabriel Stanovsky, Dafna Shahaf, and Reut Tsarfaty, Ecological semantics: Programming environments for situated language understanding
Bridging AI and Cognitive Science (BAICS) at International Conference on Learning Representations (ICLR), 2020


Ronen Tamari, Hiroyuki Shindo, Dafna Shahaf, and Yuji Matsumoto, Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text
NAACL-HLT workshop on extracting structured knowledge from scientific publications (ESSP), 2019


Aniket Kittur, Lixiu Yu, Tom Hope, Joel Chan, Hila Lifshitz-Assaf, Karni Gilon, Felicia Ng, Robert E. Kraut, and Dafna Shahaf, Scaling Up Analogy-based Innovation with Crowds and AI
PNAS 2019


Joel Chan, Joseph Chee Chang, Tom Hope, Dafna Shahaf, and Aniket Kittur, SOLVENT: A Mixed Initiative System for Finding Analogies between Research Papers
CSCW 2018


Karni Gilon, Felicia Ng, Joel Chan, Dafna Shahaf and Aniket Kittur, Analogy Mining for Specific Design Needs
CHI 2018


Tom Hope, Joel Chan, Aniket Kittur and Dafna Shahaf, Accelerating Innovation Through Analogy Mining
KDD 2017


 Best Research Paper and Best Student Research Paper, KDD'17

Joel Chan, Tom Hope, Dafna Shahaf and Aniket Kittur, Scaling up Analogy with Crowdsourcing and Machine Learning
ICCBR-16 Computational Analogy Workshop


Chen Shani, Nadav Borenstein, Dafna Shahaf, How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements
Association for Computational Linguistics (ACL), 2021


Nir Sweed, Dafna Shahaf, Catchphrase: Automatic Detection of Cultural References
Association for Computational Linguistics (ACL), 2021


Moran Mizrahi, Stav Yardeni Seelig, Dafna Shahaf, Coming to Terms: Automatic Formation of Neologisms in Hebrew
Findings of the Association for Computational Linguistics (EMNLP), 2020


David Tsurel, Michael Doron, Alexander Nus, Arnon Dagan, Ido Guy, and Dafna Shahaf, E-Commerce Dispute Resolution Prediction
CIKM, 2020