NLLP @ EMNLP 2021

12 papers

Top Research Directions

The 33 research directions with NLLP @ EMNLP 2021 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Pre-Training Language Models on Specialized Corpora433.3%
2Mitigating Optical Character Recognition Noise in Document Analysis216.7%
3Overcoming Domain Shift in Specialized Text Processing216.7%
4Adapting Language Models to Temporal Drift18.3%
5Boilerplate Interference in Web Crawled Text18.3%
6Calibrating Uncertainty in Deep Neural Networks18.3%
7Context Preserving Segmentation for Long Text Processing18.3%
8Context Window Constraints in Transformer Architectures18.3%
9Contrastive Term Weighting for Specialized Domains18.3%
10Cross-Jurisdictional Generalizability in Legal AI18.3%
11Data Quality Over Quantity in Language Model Training18.3%
12Domain Specific Stopword Removal and Vocabulary Filtering18.3%
13Integrating Symbolic Rules and Statistical Language Models18.3%
14Layout Aware Representations for Visually Rich Documents18.3%
15Mapping Colloquial Language to Clinical Ontologies18.3%
16Modeling Hierarchical Structure in Long Documents18.3%
17Modeling Morphologically Rich Low Resource Languages18.3%
18Negative Constraints for High Precision Information Retrieval18.3%
19Overcoming Majority Class Bias in Imbalanced Classification18.3%
20Overcoming the Expert Annotation Bottleneck18.3%
21Overcoming the Knowledge Acquisition Bottleneck18.3%
22Preventing Subword Fragmentation in Specialized Language Models18.3%
23Progressive Layer Unfreezing for Model Adaptation18.3%
24Quality Aware Label Aggregation via Annotator Reliability Modeling18.3%
25Resolving Zero Anaphora in Pro Drop Languages18.3%

Download all directions as CSV

Institutions

Institutions credited by NLLP @ EMNLP 2021 papers: a paper credits every institution named in its affiliations, once. 19 institutions share 12 credited papers.

#InstitutionPapersShare
1Stanford University 216.7%
2The University of Melbourne 216.7%
3The University of Queensland 216.7%
400q3tc787 18.3%
5029hcca68 18.3%
6Athens University of Economics and Business 18.3%
7Bar-Ilan University 18.3%
8ETH Zurich 18.3%
9Harvard University 18.3%
10Hebrew University of Jerusalem 18.3%
11HEC Paris 18.3%
12New York University 18.3%
13Universitatea Națională de Știință și Tehnologie Politehnica București 18.3%
14University of Bern 18.3%
15University of Bucharest 18.3%
16University of Copenhagen 18.3%
17University of Liège 18.3%
18University of Zurich 18.3%
19École Polytechnique 18.3%

Download all institutions as CSV

About this data

Papers. NLLP @ EMNLP 2021 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. 12 of 12 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 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “NLLP @ EMNLP 2021”, https://lacuna.tiptreesystems.com/venue/nllp-emnlp/2021.

Top Authors

AuthorPapers
Christopher D Manning2
Timothy Baldwin2
Hadi Abdine1
Joel Niklaus1
Michalis Vazirgiannis1
Mihai Masala1
Nhi Pham1
Simon Clematide1
Traian Rebedea1

Impactful Papers

Papers from NLLP @ EMNLP 2021 that shaped research clusters.

Influential

Papers

Title
Automated Extraction of Sentencing Decisions from Court Cases in the Hebrew Language
Automatic Resolution of Domain Name Disputes
Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser
jurBERT: A Romanian BERT Model for Legal Judgement Prediction
JuriBERT: A Masked-Language Model Adaptation for French Legal Text
Learning from Limited Labels for Long Legal Dialogue
Legal Terminology Extraction with the Termolator
Machine Extraction of Tax Laws from Legislative Texts
Named Entity Recognition in Historic Legal Text: A Transformer and State Machine Ensemble Method
Searching for Legal Documents at Paragraph Level: Automating Label Generation and Use of an Extended Attention Mask for Boosting Neural Models of Semantic Similarity
Semi-automatic Triage of Requests for Free Legal Assistance
Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark