Incorporating Demographic Factors into Natural Language Processing Models

Risultati finali

Data Management Plan of the project

Pubblicazioni

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

Autori: Lauscher, Anne; Bianchi, Federico; Bowman, Samuel R.; Hovy, Dirk
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Pagina/e 7901–7918
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-main.539

XLM-EMO: Multilingual Emotion Prediction in Social Media Text

Autori: Federico Bianchi, Debora Nozza, Dirk Hovy
Pubblicato in: Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, 2022, Pagina/e 195–203
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.wassa-1.18

Pipelines for Social Bias Testing of Large Language Models

Autori: Debora Nozza, Federico Bianchi, Dirk Hovy
Pubblicato in: "Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models", 2022
Editore: ACL

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

Autori: Tommaso Fornaciari; Alexandra Uma; Massimo Poesio; Dirk Hovy
Pubblicato in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2022, Pagina/e 127–134
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-demo.12

Fair and Argumentative Language Modeling for Computational Argumentation

Autori: Carolin Holtermann, Anne Lauscher, Simone Ponzetto
Pubblicato in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Numero 1, 2022, Pagina/e 7841–7861
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-long.541

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

Autori: Chia-Chien Hung; Anne Lauscher; Simone Ponzetto; Goran Glavaš
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2022, Numero 1, 2022, Pagina/e 891–904
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.findings-acl.72

Pipelines for Social Bias Testing of Large Language Models

Autori: Debora Nozza; Federico Bianchi; Dirk Hovy
Pubblicato in: "Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models", Numero 1, 2022, Pagina/e 68–74
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.bigscience-1.6

Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals

Autori: Debora Nozza, Federico Bianchi, Anne Lauscher, Dirk Hovy
Pubblicato in: Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion, 2022
Editore: ACL

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

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

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks

Autori: Paul Rottger; Bertie Vidgen; Dirk Hovy; Janet Pierrehumbert
Pubblicato in: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022, Pagina/e 175–190
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.naacl-main.13

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

Autori: Dirk Hovy, Diyi Yang
Pubblicato in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Stroudsberg, PA, 2021
Editore: ACL

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

Autori: Alba Cercas Curry, Amanda Cercas Curry
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, Pagina/e 8123–8130
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.515

HONEST: Measuring Hurtful Sentence Completion in Language Models

Autori: Debora Nozza, Federico Bianchi, Dirk Hovy
Pubblicato in: In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Stroudsberg, PA, 2021
Editore: ACL

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

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

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

Autori: Anne Lauscher, Debora Nozza, Ehm Miltersen, Archie Crowley, Dirk Hovy
Pubblicato in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Numero 1, 2023, Pagina/e 377–392
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.23

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

Autori: Debora Nozza
Pubblicato 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), Numero 2, 2021, Pagina/e 907–914
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-short.114

Bridging Fairness and Environmental Sustainability in Natural Language Processing

Autori: Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Pagina/e 7817–7836
Editore: 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

Autori: Gavin Abercrombie, Dirk Hovy, Vinodkumar Prabhakaran
Pubblicato in: Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), 2023, Pagina/e 96–103
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.law-1.10

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

Autori: Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis
Pubblicato in: Findings of ACL 2022, 2022
Editore: ACL

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

Autori: Chia-Chien Hung, Anne Lauscher, Dirk Hovy, Simone Paolo Ponzetto, Goran Glavaš
Pubblicato in: Findings of the Association for Computational Linguistics: EACL 2023, 2023, Pagina/e 1565–1580
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-eacl.116

HONEST: Measuring Hurtful Sentence Completion in Language Models

Autori: Debora Nozza; Federico Bianchi; Dirk Hovy
Pubblicato in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Numero 1, 2021, Pagina/e 2398–2406
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.191

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

Autori: Röttger, Paul; Nozza, Debora; Bianchi, Federico; Hovy, Dirk
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Pagina/e 5674–5691
Editore: 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

Autori: Dirk Hovy; Diyi Yang
Pubblicato in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Numero 1, 2021, Pagina/e 588–602
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.49

Language Invariant Properties in Natural Language Processing

Autori: Federico Bianchi; Debora Nozza; Dirk Hovy
Pubblicato in: Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022, Pagina/e 84–92
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.nlppower-1.9

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

Autori: Giuseppe Attanasio, , Debora Nozza, , Eliana Pastor, Dirk Hovy
Pubblicato in: Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, 2022
Editore: ACL

The State of Profanity Obfuscation in Natural Language Processing Scientific Publications

Autori: Debora Nozza, Dirk Hovy
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, Pagina/e 3897–3909
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.240

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

Autori: Federico Bianchi, Vincenzo Cutrona, Dirk Hovy
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2022, Pagina/e 289–297
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-demos.29

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

Autori: Debora Nozza
Pubblicato in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Stroudsberg, PA, 2021
Editore: ACL

Sustainable Modular Debiasing of Language Models

Autori: Anne Lauscher; Tobias Lueken; Goran Glavaš
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, Pagina/e 4782–4797
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.findings-emnlp.411

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

Autori: Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy
Pubblicato in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Numero 2, 2023, Pagina/e 1017–1029
Editore: 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

Autori: Lauscher, Anne; Crowley, Archie; Hovy, Dirk
Pubblicato in: Proceedings of the 29th International Conference on Computational Linguistics, 2022, Pagina/e 1221–1232
Editore: International Committee on Computational Linguistics

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

Autori: Bergman, A. Stevie; Abercrombie, Gavin; Spruit, Shannon; Hovy, Dirk; Dinan, Emily; Boureau, Y-Lan; Verena Rieser
Pubblicato in: Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022, Pagina/e 39–52
Editore: Association for Computational Linguistics

Five sources of bias in natural language processing

Autori: Dirk Hovy, Shrimai Prabhumoye
Pubblicato in: Language and Linguistics Compass, Wiley, 2021, ISSN 1749-818X
Editore: Blackwell
DOI: 10.1111/lnc3.12432

Viewpoint: Artificial Intelligence Accidents Waiting to Happen?

Autori: Federico Bianchi, Amanda Cercas Curry, Dirk Hovy
Pubblicato in: Journal of Artificial Intelligence Research, Numero Vol. 76 (2023), 2023, ISSN 1076-9757
Editore: Morgan Kaufmann Publishers, Inc.
DOI: 10.1613/jair.1.14263

Risultati finali

Pubblicazioni

Condividi questa pagina

Scarica