Incorporating Demographic Factors into Natural Language Processing Models

Project Information

INTEGRATOR

Grant agreement ID: 949944

DOI 10.3030/949944

EC signature date 13 November 2020

Start date 1 March 2021

End date 31 August 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost € 1 498 937,00

EU contribution € 1 498 937,00

Coordinated by

UNIVERSITA COMMERCIALE LUIGI BOCCONI
Italy

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Deliverables

Open Research Data Pilot (1)

Data Management Plan (DMP)

Data Management Plan of the project

Publications

Conference proceedings (28)

SocioProbe: What, When, and Where Language Models Learn about Sociodemographics

Author(s): Lauscher, Anne; Bianchi, Federico; Bowman, Samuel R.; Hovy, Dirk
Published in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Page(s) 7901–7918
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-main.539

XLM-EMO: Multilingual Emotion Prediction in Social Media Text

Author(s): Federico Bianchi, Debora Nozza, Dirk Hovy
Published in: Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 2022, Page(s) 195–203
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.wassa-1.18

Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa

Author(s): Tommaso Fornaciari; Alexandra Uma; Massimo Poesio; Dirk Hovy
Published in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2022, Page(s) 127–134
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-demo.12

Fair and Argumentative Language Modeling for Computational Argumentation

Author(s): Carolin Holtermann, Anne Lauscher, Simone Ponzetto
Published in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Issue 1, 2022, Page(s) 7841–7861
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-long.541

DS-TOD: Efficient Domain Specialization for Task-Oriented Dialog

Author(s): Chia-Chien Hung; Anne Lauscher; Simone Ponzetto; Goran Glavaš
Published in: Findings of the Association for Computational Linguistics: ACL 2022, Issue 1, 2022, Page(s) 891–904
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.findings-acl.72

Pipelines for Social Bias Testing of Large Language Models

Author(s): Debora Nozza; Federico Bianchi; Dirk Hovy
Published in: "Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models", Issue 1, 2022, Page(s) 68–74
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.bigscience-1.6

Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals

Author(s): Debora Nozza; Federico Bianchi; Anne Lauscher; Dirk Hovy
Published in: Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion, 2022, Page(s) 26–34
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.ltedi-1.4

SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems

Author(s): Emily Dinan; Gavin Abercrombie; A. Bergman; Shannon Spruit; Dirk Hovy; Y-Lan Boureau; Verena Rieser
Published in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, Page(s) 4113–4133
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-long.284

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks

Author(s): Paul Rottger; Bertie Vidgen; Dirk Hovy; Janet Pierrehumbert
Published in: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022, Page(s) 175–190
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.naacl-main.13

Computer says “No”: The Case Against Empathetic Conversational AI

Author(s): Alba Cercas Curry, Amanda Cercas Curry
Published in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, Page(s) 8123–8130
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.515

MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection

Author(s): Amanda Cercas Curry, Giuseppe Attanasio, Debora Nozza, Dirk Hovy
Published in: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), 2023, Page(s) 2067–2074
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.semeval-1.285

What about “em”? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns

Author(s): Anne Lauscher, Debora Nozza, Ehm Miltersen, Archie Crowley, Dirk Hovy
Published in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Issue 1, 2023, Page(s) 377–392
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.23

Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection

Author(s): Debora Nozza
Published in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Issue 2, 2021, Page(s) 907–914
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-short.114

Bridging Fairness and Environmental Sustainability in Natural Language Processing

Author(s): Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher
Published in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Page(s) 7817–7836
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-main.533

Temporal and Second Language Influence on Intra-Annotator Agreement and Stability in Hate Speech Labelling

Author(s): Gavin Abercrombie, Dirk Hovy, Vinodkumar Prabhakaran
Published in: Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), 2023, Page(s) 96–103
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.law-1.10

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

Author(s): Giuseppe Attanasio; Debora Nozza; Dirk Hovy; Elena Baralis
Published in: Findings of the Association for Computational Linguistics: ACL 2022, 2022, Page(s) 1105–1119
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.findings-acl.88

Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers

Author(s): Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavaš
Published in: Findings of the Association for Computational Linguistics: EACL 2023, 2023, Page(s) 1565–1580
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-eacl.116

HONEST: Measuring Hurtful Sentence Completion in Language Models

Author(s): Debora Nozza; Federico Bianchi; Dirk Hovy
Published in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Issue 1, 2021, Page(s) 2398–2406
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.191

Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages

Author(s): Röttger, Paul; Nozza, Debora; Bianchi, Federico; Hovy, Dirk
Published in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Page(s) 5674–5691
Publisher: Association for Computational Linguistics Abu Dhabi, United Arab Emirates
DOI: 10.18653/v1/2022.emnlp-main.383

The Importance of Modeling Social Factors of Language: Theory and Practice

Author(s): Dirk Hovy; Diyi Yang
Published in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Issue 1, 2021, Page(s) 588–602
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.49

Language Invariant Properties in Natural Language Processing

Author(s): Federico Bianchi; Debora Nozza; Dirk Hovy
Published in: Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022, Page(s) 84–92
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.nlppower-1.9

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection

Author(s): Giuseppe Attanasio; Debora Nozza; Eliana Pastor; Dirk Hovy
Published in: Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022, Page(s) 100–112
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.nlppower-1.11

The State of Profanity Obfuscation in Natural Language Processing Scientific Publications

Author(s): Debora Nozza, Dirk Hovy
Published in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, Page(s) 3897–3909
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.240

Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data

Author(s): Federico Bianchi, Vincenzo Cutrona, Dirk Hovy
Published in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2022, Page(s) 289–297
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-demos.29

Sustainable Modular Debiasing of Language Models

Author(s): Anne Lauscher; Tobias Lueken; Goran Glavaš
Published in: Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, Page(s) 4782–4797
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.findings-emnlp.411

The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics

Author(s): Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy
Published in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Issue 2, 2023, Page(s) 1017–1029
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-short.88

Welcome to the modern world of pronouns: identity-inclusive Natural Language Processing beyond gender

Author(s): Lauscher, Anne; Crowley, Archie; Hovy, Dirk
Published in: Proceedings of the 29th International Conference on Computational Linguistics, 2022, Page(s) 1221–1232
Publisher: International Committee on Computational Linguistics

Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design

Author(s): Bergman, A. Stevie; Abercrombie, Gavin; Spruit, Shannon; Hovy, Dirk; Dinan, Emily; Boureau, Y-Lan; Verena Rieser
Published in: Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022, Page(s) 39–52
Publisher: Association for Computational Linguistics

Peer reviewed articles (2)

Five sources of bias in natural language processing

Author(s): Dirk Hovy, Shrimai Prabhumoye
Published in: Language and Linguistics Compass, Wiley, 2021, ISSN 1749-818X
Publisher: Blackwell
DOI: 10.1111/lnc3.12432

Viewpoint: Artificial Intelligence Accidents Waiting to Happen?

Author(s): Federico Bianchi, Amanda Cercas Curry, Dirk Hovy
Published in: Journal of Artificial Intelligence Research, Issue Vol. 76 (2023), 2023, ISSN 1076-9757
Publisher: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.14263