Tds 2021
Top Research Directions
The 4 research directions with Tds 2021 papers, ranked by paper count, next to 2020. Share is the fraction of the edition’s papers in the direction.
| # | Direction | 2021 | 2020 | Share 2021 | Share 2020 | 2020 rank |
|---|---|---|---|---|---|---|
| 1 | Overcoming Parameter Dilution with Monolingual Pretraining | 1 | 0 | 14.3% | 0.0% | — |
| 2 | The Capacity Bottleneck in Massively Multilingual Models | 1 | 0 | 14.3% | 0.0% | — |
| 3 | The Mechanics of Subword Tokenization | 1 | 0 | 14.3% | 0.0% | — |
| 4 | The Performance Advantage of Localized Language Pretraining | 1 | 0 | 14.3% | 0.0% | — |
Download all directions as CSV
Institutions
Institutions credited by Tds 2021 papers: a paper credits every institution named in its affiliations, once. 3 institutions share 2 credited papers.
| # | Institution | Papers | Share | 2020 | 2020 rank |
|---|---|---|---|---|---|
| 1 | Amazon (United States) | 1 | 50.0% | 0 | — |
| 2 | Charles University | 1 | 50.0% | 1 | 5 |
| 3 | University of Edinburgh | 1 | 50.0% | 0 | — |
Download all institutions as CSV
About this data
Papers. Tds 2021 lists 7 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.
Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2020 use shares, since the edition went from 12 to 7 papers.
Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 2 of 7 papers (28.6%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.
Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Tds 2021”, https://lacuna.tiptreesystems.com/venue/tds/2021.