CALCS @ EMNLP 2023

5 papers

Top Research Directions

The 10 research directions with CALCS @ EMNLP 2023 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1External Language Model Integration for Neural Speech Recognition240.0%
2Overcoming Data Scarcity in Code-Switched Language Modeling240.0%
3Robust Speech Recognition for Intra-Sentential Code-Switching240.0%
4Bridging the Read to Spontaneous Speech Gap120.0%
5Bridging the Synthetic to Natural Code Switching Gap120.0%
6Polyphone Disambiguation for Text to Speech Synthesis120.0%
7Rotary Position Embeddings in Sequence Modeling120.0%
8Syntactic Structural Variance and Cross-Linguistic Generalizability120.0%
9Synthetic Data Generation for Code-Switched Language Processing120.0%
10The Performance Advantage of Localized Language Pretraining120.0%

Download all directions as CSV

Institutions

Institutions credited by CALCS @ EMNLP 2023 papers: a paper credits every institution named in its affiliations, once. 13 institutions share 5 credited papers.

#InstitutionPapersShare
1Stanford University 360.0%
2National University of Singapore 240.0%
3University of California, Los Angeles 240.0%
4Amazon (United States) 120.0%
5Brown University 120.0%
6Chinese University of Hong Kong, Shenzhen 120.0%
7Mohamed bin Zayed University of Artificial Intelligence 120.0%
8Nvidia (United States) 120.0%
9San Diego State University 120.0%
10San Jose State University 120.0%
11University of California, Berkeley 120.0%
12University of Potsdam 120.0%
13University of South Carolina 120.0%

Download all institutions as CSV

About this data

Papers. CALCS @ EMNLP 2023 lists 5 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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. 5 of 5 papers (100.0%) 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, “CALCS @ EMNLP 2023”, https://lacuna.tiptreesystems.com/venue/calcs-emnlp/2023.

Top Authors

AuthorPapers
Alham Fikri Aji1
Aman Chadha1
Amitava Das1
Anubhab Chatterjee1
Arjun Subramonian1
Boris Ginsburg1
Christopher D Manning1
Dan Jurafsky1
Dima Rekesh1
Genta Indra Winata1
Haizhou Li1
Holy Lovenia1
Jan Christian Blaise Cruz1
Jessica Zosa Forde1
Kunal Dhawan1
Lintang Sutawika1
Long Phan1
Mohsin Ali Mohammed1
Neeharika Gupta1
Parth Patwa1

Impactful Papers

Papers from CALCS @ EMNLP 2023 that shaped research clusters.

Influential

Papers

Title
CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling
Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching
Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages
Text-Derived Language Identity Incorporation for End-to-End Code-Switching Speech Recognition
Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer