NLLP @ EMNLP 2022

8 papers

Top Research Directions

The 23 research directions with NLLP @ EMNLP 2022 papers, ranked by paper count, next to 2021. Share is the fraction of the edition’s papers in the direction.

#Direction20222021Share 2022Share 20212021 rank
1Deconstructing Complex Legal and Regulatory Documents3037.5%0.0%—
2Cross-Jurisdictional Generalizability in Legal AI2125.0%8.3%10
3Modeling the Linguistic Complexity of Legal Text2025.0%0.0%—
4Adapting Classification Techniques to Open Ended Generation1012.5%0.0%—
5Adapting Foundation Models with Fractional Parameter Updates1012.5%0.0%—
6Adapting Language Models via Continual Pre-training1012.5%0.0%—
7Bridging the Parameter Efficient Fine Tuning Performance Gap1012.5%0.0%—
8Context Window Constraints in Transformer Architectures1112.5%8.3%8
9Contextual Language Modeling for Nuanced Text Classification1012.5%0.0%—
10Continuous Prompt Tuning for Large Pre-trained Models1012.5%0.0%—
11Domain Adaptation under Extreme Target Data Scarcity1012.5%0.0%—
12Domain Adaptive Pre Training of Language Models1012.5%0.0%—
13Gradient-Based Feature Attribution for Language Models1012.5%0.0%—
14Mapping Political Identity and Behavior Through Linguistic Style1012.5%0.0%—
15Post-Hoc Logit Scaling for Probability Calibration1012.5%0.0%—
16Pre-Training Language Models on Specialized Corpora1412.5%33.3%1
17Retrospective Bias in Legal Judgment Prediction1012.5%0.0%—
18Rhetorical and Functional Role Labeling of Text1012.5%0.0%—
19Robustness to Formal and Informal Domain Shift1112.5%8.3%27
20Scaling Transformers with Sparse Attention Mechanisms1012.5%0.0%—
21The Language Bias of English Centric Benchmarks1012.5%0.0%—
22Transferring Soft Prompts Across Tasks1012.5%0.0%—
23Zero-Shot Classification via Natural Language Inference1012.5%0.0%—

Download all directions as CSV

Institutions

Institutions credited by NLLP @ EMNLP 2022 papers: a paper credits every institution named in its affiliations, once. 9 institutions share 7 credited papers.

#InstitutionPapersShare20212021 rank
105t1d6r64 114.3%0—
2Amazon (United States) 114.3%0—
3Columbia University 114.3%0—
4Indian Institute of Technology Kanpur 114.3%0—
5Korea Advanced Institute of Science and Technology 114.3%0—
6Queen's University 114.3%0—
7University of Ottawa 114.3%0—
8Utrecht University 114.3%0—
9West Bengal National University of Juridical Sciences 114.3%0—

Download all institutions as CSV

About this data

Papers. NLLP @ EMNLP 2022 lists 8 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. Comparisons with 2021 use shares, since the edition went from 12 to 8 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 8 papers (87.5%) 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, “NLLP @ EMNLP 2022”, https://lacuna.tiptreesystems.com/venue/nllp-emnlp/2022.

Top Authors

AuthorPapers
Albert Gatt1
Ashutosh Modi1
Gil Semo1
Joel Niklaus1
Kathleen McKeown1
Minjoon Seo1
Noah Bergam1
Rashmi Gangadharaiah1
Xiaodan Zhu1

Impactful Papers

Papers from NLLP @ EMNLP 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Automatic Classification of Legal Violations in Cookie Banner Texts
ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US
Data-efficient end-to-end Information Extraction for Statistical Legal Analysis
Detecting Relevant Differences Between Similar Legal Texts
Legal and Political Stance Detection of SCOTUS Language
Parameter-Efficient Legal Domain Adaptation
Semantic Segmentation of Legal Documents via Rhetorical Roles
Towards Cross-Domain Transferability of Text Generation Models for Legal Text