Header

UZH-Logo

Maintenance Infos

Embedding-based Scientific Literature Discovery in a Text Editor Application


Gökçe, Onur; Prada, Jonathan; Nikolov, Nikola I; Gu, Nianlong; Hahnloser, Richard H R (2020). Embedding-based Scientific Literature Discovery in a Text Editor Application. In: The 58th annual meeting of the Association for Computational Linguistics (ACL), Virtual Conference, 5 July 2020 - 10 July 2020.

Abstract

Each claim in a research paper requires all rel-evant prior knowledge to be discovered, as-similated, and appropriately cited. However,despite the availability of powerful search en-gines and sophisticated text editing software,discovering relevant papers and integrating theknowledge into a manuscript remain complextasks associated with high cognitive load. Todefine comprehensive search queries requiresstrong motivation from authors, irrespective oftheir familiarity with the research field. More-over, switching between independent appli-cations for literature discovery, bibliographymanagement, reading papers, and writing textburdens authors further and interrupts their cre-ative process. Here, we present a web applica-tion that combines text editing and literaturediscovery in an interactive user interface. Theapplication is equipped with a search enginethat couples Boolean keyword filtering withnearest neighbor search over text embeddings,providing a discovery experience tuned to anauthor’s manuscript and his interests. Our ap-plication aims to take a step towards more en-joyable and effortless academic writing.

Abstract

Each claim in a research paper requires all rel-evant prior knowledge to be discovered, as-similated, and appropriately cited. However,despite the availability of powerful search en-gines and sophisticated text editing software,discovering relevant papers and integrating theknowledge into a manuscript remain complextasks associated with high cognitive load. Todefine comprehensive search queries requiresstrong motivation from authors, irrespective oftheir familiarity with the research field. More-over, switching between independent appli-cations for literature discovery, bibliographymanagement, reading papers, and writing textburdens authors further and interrupts their cre-ative process. Here, we present a web applica-tion that combines text editing and literaturediscovery in an interactive user interface. Theapplication is equipped with a search enginethat couples Boolean keyword filtering withnearest neighbor search over text embeddings,providing a discovery experience tuned to anauthor’s manuscript and his interests. Our ap-plication aims to take a step towards more en-joyable and effortless academic writing.

Statistics

Downloads

2 downloads since deposited on 16 Feb 2021
2 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:10 July 2020
Deposited On:16 Feb 2021 08:29
Last Modified:16 Feb 2021 20:30
Publisher:Association for Computational Linguistics
OA Status:Green

Download

Green Open Access

Download PDF  'Embedding-based Scientific Literature Discovery in a Text Editor Application'.
Preview
Content: Published Version
Filetype: PDF
Size: 805kB