Wanlp 2021

10 papers

Top Research Directions

The 30 research directions with Wanlp 2021 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Adapting Natural Language Processing to Dialectal Diversity550.0%
2Discriminating Between Closely Related Languages and Dialects330.0%
3Fine Grained and Multi Target Offensive Language Detection220.0%
4Adapting Multilingual Models to Low Resource Languages110.0%
5Algorithmic Strategies for Scalable Content Moderation110.0%
6Auditing Failure Modes Beyond Aggregate Performance Metrics110.0%
7Benchmarking Deep Learning Against Traditional Machine Learning110.0%
8Bottleneck Adapters for Parameter Efficient Fine Tuning110.0%
9Character N-Gram Embeddings for Robust Word Representations110.0%
10Class Imbalance in Linguistic Variety Identification110.0%
11Dialogue History Integration for Resolving Emotional Ambiguity110.0%
12Empathetic Response Generation for Conversational AI110.0%
13Fusing Heterogeneous Vector Spaces for Robust Text Representation110.0%
14Hierarchical Feature Abstraction Across Transformer Layers110.0%
15Hybrid Convolutional Recurrent Architectures for Sequence Modeling110.0%
16Measuring Inter-Annotator Agreement for Reliable Data Curation110.0%
17Model Ensembling for Robustness and Generalization110.0%
18Modeling Semantic Inversion in Sarcasm Detection110.0%
19Morphological Misalignment in Subword Tokenization110.0%
20Multi-Granular Representation Fusion in Language Models110.0%
21Nuanced Detection and Mitigation of Online Harm110.0%
22Overcoming Data Scarcity for Low Resource Dialectal Modeling110.0%
23Phrase Level Simplification of Multi Word Expressions110.0%
24Projecting Intermediate Transformer States to the Vocabulary Space110.0%
25Robust Speech Recognition for Intra-Sentential Code-Switching110.0%

Download all directions as CSV

Institutions

Institutions credited by Wanlp 2021 papers: a paper credits every institution named in its affiliations, once. 13 institutions share 10 credited papers.

#InstitutionPapersShare
1Hamad bin Khalifa University 330.0%
2New York University 330.0%
3New York University Abu Dhabi 330.0%
4Qatar Computing Research Institute 330.0%
5Carnegie Mellon University Qatar 220.0%
602ma4wv74 110.0%
7American University of Beirut 110.0%
8Carnegie Mellon University 110.0%
9King Saud University 110.0%
10Microsoft (United States) 110.0%
11University of Birmingham 110.0%
12University of British Columbia 110.0%
13Özyeğin University 110.0%

Download all institutions as CSV

About this data

Papers. Wanlp 2021 lists 10 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. 10 of 10 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, “Wanlp 2021”, https://lacuna.tiptreesystems.com/venue/wanlp/2021.

Top Authors

AuthorPapers
Ahmed Abdelali3
Nizar Habash3
Badr AlKhamissi1
Mark G. Lee1
Muhammad ElNokrashy1
Nora Al-Twairesh1
Tarek Naous1

Impactful Papers

Papers from Wanlp 2021 that shaped research clusters.

Influential

Papers

Title
Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task
Adult Content Detection on Arabic Twitter: Analysis and Experiments
Arabic Offensive Language on Twitter: Analysis and Experiments
Automatic Romanization of Arabic Bibliographic Records
Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data
Multi-task Learning Using a Combination of Contextualised and Static Word Embeddings for Arabic Sarcasm Detection and Sentiment Analysis
NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task
QADI: Arabic Dialect Identification in the Wild
The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models
What does BERT Learn from Arabic Machine Reading Comprehension Datasets?