WANLP @ EMNLP 2022

14 papers

Top Research Directions

The 39 research directions with WANLP @ EMNLP 2022 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Adapting Language Models to Temporal Drift214.3%
2Modeling the Divergence Between Formal Standards and Spoken Dialects214.3%
3Orthographic Normalization for Dialectal and Informal Text214.3%
4The Dialectal Representation Gap in Language Models214.3%
5The Performance Advantage of Localized Language Pretraining214.3%
6Adapting Natural Language Processing to Dialectal Diversity17.1%
7Asymmetric Performance in Multilingual Generation and Translation17.1%
8Cascaded Pipelines for Spoken Language Translation17.1%
9Classifying High Variance and Catch All Semantic Categories17.1%
10Control Tokens for Attribute Conditioned Sequence Generation17.1%
11Discriminating Between Closely Related Languages and Dialects17.1%
12Factual Consistency in Abstractive Summarization17.1%
13Fine-Grained Identification of Manipulative Rhetoric17.1%
14Hierarchical Lexical Inheritance for Efficient Language Modeling17.1%
15Joint Encoder Decoder Pre training17.1%
16Joint Multilingual Training for Cross-Lingual Transfer17.1%
17Language Identification in Short Texts17.1%
18Learning from Factually Inconsistent Reference Summaries17.1%
19Mitigating Monolingual Bias in Code-Switched Language Models17.1%
20Morphological Bias in Machine Translation Evaluation17.1%
21Multi-Label Language and Dialect Identification17.1%
22Nonparametric Methods for Robust Group and Distribution Comparison17.1%
23Orthographic Inconsistency in Low Resource Language Processing17.1%
24Overcoming Data Scarcity for Low Resource Dialectal Modeling17.1%
25Overcoming Error Propagation in Cascaded Speech Pipelines17.1%

Download all directions as CSV

Institutions

Institutions credited by WANLP @ EMNLP 2022 papers: a paper credits every institution named in its affiliations, once. 28 institutions share 14 credited papers.

#InstitutionPapersShare
1New York University 535.7%
2New York University Abu Dhabi 535.7%
3Carnegie Mellon University Qatar 214.3%
4Hamad bin Khalifa University 214.3%
5Mohamed bin Zayed University of Artificial Intelligence 214.3%
6Qatar Computing Research Institute 214.3%
7University of British Columbia 214.3%
802ma4wv74 17.1%
9Alexandria University 17.1%
10Amazon (United States) 17.1%
11Carnegie Mellon University 17.1%
12Centre National de la Recherche Scientifique 17.1%
13German University in Cairo 17.1%
14Indian Institute of Technology Delhi 17.1%
15King Abdulaziz City for Science and Technology 17.1%
16King Saud University 17.1%
17Laboratoire d'Informatique de Paris-Nord 17.1%
18Meta (United States) 17.1%
19Taif University 17.1%
20University of Delaware 17.1%
21University of Manchester 17.1%
22University of Oxford 17.1%
23University of Padua 17.1%
24University of Sheffield 17.1%
25University of Stuttgart 17.1%
26Université Sorbonne Paris Nord 17.1%
27École Polytechnique 17.1%
28Özyeğin University 17.1%

Download all institutions as CSV

About this data

Papers. WANLP @ EMNLP 2022 lists 14 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. 14 of 14 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 2026-11-17 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “WANLP @ EMNLP 2022”, https://lacuna.tiptreesystems.com/venue/wanlp-emnlp/2022.

Top Authors

AuthorPapers
Nizar Habash4
Hamdy Mubarak2
Preslav Nakov2
Abdullah Khered1
Abdulmohsen Al-Thubaity1
Ahmed Abdelali1
Fahim Dalvi1
Firoj Alam1
Giovanni Da San Martino1
Injy Hamed1
Joseph Le Roux1
Laks V. S. Lakshmanan1
Marwan Torki1
Nadir Durrani1
Nadi Tomeh1
Olga Golovneva1
Riza Batista-Navarro1
Robert J. Gaizauskas1
Shubham Mittal1
Thang Vu1

Impactful Papers

Papers from WANLP @ EMNLP 2022 that shaped research clusters.

Influential

Papers

Title
A Benchmark Study of Contrastive Learning for Arabic Social Meaning
A Pilot Study on the Collection and Computational Analysis of Linguistic Differences Amongst Men and Women in a Kuwaiti Arabic WhatsApp Dataset
AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization
AraDepSu: Detecting Depression and Suicidal Ideation in Arabic Tweets Using Transformers
ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic-English
Building an Ensemble of Transformer Models for Arabic Dialect Classification and Sentiment Analysis
CAraNER: The COVID-19 Arabic Named Entity Corpus
Cross-lingual transfer for low-resource Arabic language understanding
IITD at WANLP 2022 Shared Task: Multilingual Multi-Granularity Network for Propaganda Detection
Maknuune: A Large Open Palestinian Arabic Lexicon
NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task
NatiQ: An End-to-end Text-to-Speech System for Arabic
Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic
The Shared Task on Gender Rewriting