Analogy Search Engine: Finding Analogies in Cross-Domain Research Papers

TL;DR

This paper introduces the Analogy Search Engine (ASE), a semantic search tool that leverages computational analogy and NLP to discover cross-domain research papers, surpassing traditional keyword-based methods.

Contribution

The paper presents a novel semantic search engine that identifies analogical relationships among research papers across domains, improving retrieval of relevant interdisciplinary research.

Findings

ASE finds more interesting papers than baseline elasticsearch.

ASE effectively discovers deeper analogical relationships.

Methods applicable beyond academic papers to other document search tasks.

Abstract

In recent years, with the rapid proliferation of research publications in the field of Artificial Intelligence, it is becoming increasingly difficult for researchers to effectively keep up with all the latest research in one's own domains. However, history has shown that scientific breakthroughs often come from collaborations of researchers from different domains. Traditional search algorithms like Lexical search, which look for literal matches or synonyms and variants of the query words, are not effective for discovering cross-domain research papers and meeting the needs of researchers in this age of information overflow. In this paper, we developed and tested an innovative semantic search engine, Analogy Search Engine (ASE), for 2000 AI research paper abstracts across domains like Language Technologies, Robotics, Machine Learning, Computational Biology, Human Computer Interactions, etc. ASE combines recent theories and methods from Computational Analogy and Natural Language Processing to go beyond keyword-based lexical search and discover the deeper analogical relationships among research paper abstracts. We experimentally show that ASE is capable of finding more interesting and useful research papers than baseline elasticsearch. Furthermore, we believe that the methods used in ASE go beyond academic paper and will benefit many other document search tasks.