Embedding-based Scientific Literature Discovery in a Text Editor Application
This addresses the challenge for researchers who face high cognitive load and workflow interruptions when switching between separate tools for literature discovery and writing, though it is incremental as it combines existing methods in a new interface.
The paper tackles the problem of discovering relevant scientific literature while writing manuscripts by developing a web application that integrates text editing with a search engine using Boolean keyword filtering and nearest neighbor search over text embeddings, aiming to reduce cognitive load and improve the academic writing experience.
Each claim in a research paper requires all relevant prior knowledge to be discovered, assimilated, and appropriately cited. However, despite the availability of powerful search engines and sophisticated text editing software, discovering relevant papers and integrating the knowledge into a manuscript remain complex tasks associated with high cognitive load. To define comprehensive search queries requires strong motivation from authors, irrespective of their familiarity with the research field. Moreover, switching between independent applications for literature discovery, bibliography management, reading papers, and writing text burdens authors further and interrupts their creative process. Here, we present a web application that combines text editing and literature discovery in an interactive user interface. The application is equipped with a search engine that couples Boolean keyword filtering with nearest neighbor search over text embeddings, providing a discovery experience tuned to an author's manuscript and his interests. Our application aims to take a step towards more enjoyable and effortless academic writing. The demo of the application (https://SciEditorDemo2020.herokuapp.com/) and a short video tutorial (https://youtu.be/pkdVU60IcRc) are available online.