Tds 2020

12 papers

Top Research Directions

The 15 research directions with Tds 2020 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Beyond the Single Best Speech Recognition Hypothesis18.3%
2Differentially Private Stochastic Gradient Descent18.3%
3End-to-End Representation Learning in Natural Language Processing18.3%
4Generative Error Correction for Speech Recognition18.3%
5How Model Scale Alters Memorization and Privacy Risks18.3%
6Overcoming Cascaded Error Propagation in Spoken Language Processing18.3%
7Overcoming Fixed Window Context Constraints18.3%
8Pointer Generator Mechanisms for Grounded Text Generation18.3%
9Redundancy of Explicit Linguistic Features in Neural Encoders18.3%
10Robust Natural Language Understanding for Noisy Speech Transcripts18.3%
11Scaling Differentially Private Training by Reducing Gradient Overhead18.3%
12Speech Processing with Word Lattices and Confusion Networks18.3%
13Structural and Semantic Representations for Relation Extraction18.3%
14Synthesizing Spontaneous Speech Through Conversational Disfluencies18.3%
15Text Reconstruction Attacks on Dense Vector Representations18.3%

Download all directions as CSV

Institutions

Institutions credited by Tds 2020 papers: a paper credits every institution named in its affiliations, once. 6 institutions share 7 credited papers.

#InstitutionPapersShare
1International Institute of Information Technology, Hyderabad 342.9%
2Laboratoire d'Informatique de Grenoble 228.6%
3Saarland University 228.6%
4Université Grenoble Alpes 228.6%
5Charles University 114.3%
6Stockholm University 114.3%

Download all institutions as CSV

About this data

Papers. Tds 2020 lists 12 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 12 papers (58.3%) 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 2020”, https://lacuna.tiptreesystems.com/venue/tds/2020.

Top Authors

AuthorPapers
Manish Shrivastava2
Aditya Mogadala1
David Ifeoluwa Adelani1
Dietrich Klakow1
Joakim Nivre1
Murathan Kurfali1
Prateek Saxena1
Rudolf Rosa1
Sergey Nikolenko1
Simone Paolo Ponzetto1
Tomáš Musil1
Vaishali Pal1
Vésteinn Snæbjarnarson1

Impactful Papers

Papers from Tds 2020 that shaped research clusters.

Influential

Papers

Title
Assessing Unintended Memorization in Neural Discriminative Sequence Models
A Twitter Political Corpus of the 2019 10N Spanish Election
ConfNet2Seq - Full Length Answer Generation from Spoken Questions
ConfNet2Seq: Full Length Answer Generation from Spoken Questions
Cross-Lingual Transfer for Hindi Discourse Relation Identification
EPIE Dataset: A Corpus for Possible Idiomatic Expressions
Experimenting with Different Machine Translation Models in Medium-Resource Settings
Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks
Labeling Explicit Discourse Relations Using Pre-trained Language Models
Measuring Memorization Effect in Word-Level Neural Networks Probing
Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
Recognizing Preferred Grammatical Gender in Russian Anonymous Online Confessions