Name: Datasets for Effective Distributed Representations for Academic Expert Search
Creator: Berger, Mark
Keywords: expert search, paper representations

Research datakeyboard_double_arrow_right Dataset 19 Nov 2020Publisher:Zenodo

Authors: Berger, Mark;

doi: 10.5281/zenodo.4075166 , 10.5281/zenodo.4075181 , 10.5281/zenodo.4075167

Datasets for Effective Distributed Representations for Academic Expert Search

- Summary
- Subjects
- Related research
  (1)
- Metrics

Abstract

Dataset for the "Effective Distributed Representations for Academic Expert Search" paper published at the SDP 2020 workshop of the EMNLP conference. Two .zip archives are provided: 1) papers_and_authors_source_csvs.zip : Contains papers.csv and authors.csv, which are CSV files with the source metadata for all the ~130k papers and ~68k authors used in the final version of the system. 2) faiss_indexes.zip : Contains all the pre-populated FAISS indexes with all the embedding variations we used in our research.

Related Organizations

University of Amsterdam
Netherlands

Keywords

expert search, paper representations

1 Research products, page 1 of 1

Model outputs and species-level data for "Functional traits and climate drive interspecific differences in disturbance-induced tree mortality"
2023IsAmongTopNSimilarDocuments

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average