Interactive Natural Language Technology for Explainable Artificial Intelligence

Informations projet

NL4XAI

N° de convention de subvention: 860621

DOI

10.3030/860621

Projet clôturé

Date de signature de la CE 19 Août 2019

Date de début 1 Octobre 2019

Date de fin 30 Septembre 2024

Financé au titre de

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Coût total

€ 2 843 888,04

Contribution de l’UE

€ 2 843 888,04

Coordonné par

UNIVERSIDAD DE SANTIAGO DE COMPOSTELA
Spain

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Websites, patent fillings, videos etc. (5)

Press release 3 to media

Press release 2 to media at the NL4XAI Student & Industry Days

Press release 4 to media

Press release 4 to media at the Final Conference.

NL4XAI website and social media profiles available

NL4XAI website and social media profiles available.

Press release 2 to media

Press release 2 to media at the PhD autumn school.

Press release 1 to media

Press release 1 to media at the Initial training meeting.

Documents, reports (6)

Technical report on the state of the art in argumentation technology for XAI

Technical report on the state of the art of argumentation technology for XAI manuscript coauthored by ESR7 and ESR8

Technical report on state of the art end-to-end NLG systems

Technical report on state of the art endtoend NLG systems manuscript coauthored by ESR5 and ESR6

Technical report on state of the art XAI models

Technical report on state of the art XAI models review manuscript coauthored by ESRs 14

Technical report on the state of the art in interactive interfaces for XAI

Technical report on the state of the art in interactive interfaces for XAI manuscript coauthored by ESRs 911

Guidelines for explainable NLG evaluation

Guidelines for explainable NLG evaluation.

Comparison of content-based recommender systems versus recommender systems supported by XAI

Comparison of content-based recommender systems versus recommender systems supported by XAI.

Other (3)

Supervisory Board of the network
NL4XAI Final Conference
Recruitment strategy and call

Publications

Conference proceedings (36)

The Natural Language Pipeline, Neural Text Generation and Explainability

Auteurs: J. Faille, A. Gatt and C. Gardent
Publié dans: 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020, Page(s) 16-21
Éditeur: Association for Computational Linguistics

Detection and Analysis of Moral Values in Argumentation

Auteurs: He Zhang, Alina Landowska, Katarzyna Budzynska
Publié dans: Pre-Proceedings of A workshop affiliated with the 26th European Conference on Artificial Intelligence: Value engineering in AI., 2023
Éditeur: ECAI
DOI: 10.13140/rg.2.2.13098.59849

Towards Generating Effective Explanations of Logical Formulas: Challenges and Strategies

Auteurs: A. Mayn (ESR4-UU), K. van Deemter
Publié dans: 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020
Éditeur: Association for Computational Linguistics

Disentangling Web Search on Debated Topics: A User-Centered Exploration

Auteurs: Alisa Rieger, Suleiman Kulane, Ujwal Gadiraju, Maria Soledad Pera
Publié dans: Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, Numéro 4, 2024, Page(s) 24-35
Éditeur: ACM
DOI: 10.1145/3627043.3659559

Explaining Search Result Stances to Opinionated People

Auteurs: Zhangyi Wu; Tim Draws; Federico Cau; Francesco Barile; Alisa Rieger; Nava Tintarev
Publié dans: Communications in Computer and Information Science ISBN: 9783031440663, Numéro 2, 2023, ISBN 978-3-031-44067-0
Éditeur: Springer
DOI: 10.1007/978-3-031-44067-0_29

From Potential to Practice: Intellectual Humility During Search on Debated Topics

Auteurs: Alisa Rieger, Frank Bredius, Mariët Theune, Maria Soledad Pera
Publié dans: Proceedings of the 2024 ACM SIGIR Conference on Human Information Interaction and Retrieval, 2024
Éditeur: ACM
DOI: 10.1145/3627508.3638306

Interactive Interventions to Mitigate Cognitive Bias

Auteurs: Alisa Rieger
Publié dans: Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, 2024
Éditeur: ACM
DOI: 10.1145/3503252.3534362

Beyond Prediction Similarity: ShapGAP for Evaluating Faithful Surrogate Models in XAI

Auteurs: Ettore Mariotti, Adarsa Sivaprasad & Jose Maria Alonso Moral
Publié dans: 2023
Éditeur: Springer Link
DOI: 10.1007/978-3-031-44064-9_10

Towards Harnessing Natural Language Generation to Explain Black-box Models

Auteurs: Ettore Mariotti, Jose M. Alonso, Albert Gatt
Publié dans: 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020
Éditeur: Association for Computational Linguistics

Habemus a Right to an Explanation: so What? – A Framework on Transparency-Explainability Functionality and Tensions in the EU AI Act

Auteurs: Luca Nannini
Publié dans: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2024
Éditeur: AAAI/ACM
DOI: 10.5281/zenodo.14041249

Explaining Bayesian Networks in Natural Language: State of the Art and Challenges

Auteurs: Conor Hennessy, Alberto Bugarín, Ehud Reiter
Publié dans: 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020
Éditeur: Association for Computational Linguistics

This Item Might Reinforce Your Opinion: Obfuscation and Labeling of Search Results to Mitigate Confirmation Bias

Auteurs: Alisa Rieger, Tim Draws, Mariët Theune, Nava Tintarev
Publié dans: Proceedings of the 32st ACM Conference on Hypertext and Social Media, 2021, Page(s) 189-199, ISBN 9781450385510
Éditeur: ACM
DOI: 10.1145/3465336.3475101

Fairness in Agreement With European Values

Auteurs: Alejandra Bringas Colmenarejo, Luca Nannini, Alisa Rieger, Kristen M. Scott, Xuan Zhao, Gourab K Patro, Gjergji Kasneci, Katharina Kinder-Kurlanda
Publié dans: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 2023
Éditeur: ACM
DOI: 10.1145/3514094.3534158

Explaining data using causal Bayesian networks

Auteurs: Jaime Sevilla
Publié dans: Proceedings of the 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020, Page(s) 34-38
Éditeur: Assoication for Computational Linguistics

Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions

Auteurs: Michele Cafagna; Kees van Deemter; Albert Gatt
Publié dans: Proceedings of the Workshop on Unimodal and Multimodal Induction of Linguistic Structures (UM-IoS), Numéro 10, 2022
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2022.umios-1.6

Is Shortest Always Best? The Role of Brevity in Logic-to-Text Generation

Auteurs: Eduardo Calò, Jordi Levy, Albert Gatt, Kees Van Deemter
Publié dans: Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), 2023
Éditeur: ACL
DOI: 10.18653/v1/2023.starsem-1.17

Towards Healthy Engagement with Online Debates

Auteurs: Alisa Rieger, Qurat-Ul-Ain Shaheen, Carles Sierra, Mariet Theune, Nava Tintarev
Publié dans: Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, 2023
Éditeur: ACM
DOI: 10.1145/3511047.3537692

Prometheus: Harnessing Fuzzy Logic and Natural Language for Human-centric Explainable Artificial Intelligence

Auteurs: Ettore Mariotti, Jose M. Alonso-Moral, Albert Gatt
Publié dans: XIX Conference of the Spanish Association for Artificial Intelligence (CAEPIA)-ESTYLF-CEDI 2021, 2021
Éditeur: XIX Conference of the Spanish Association for Artificial Intelligence (CAEPIA)-ESTYLF-CEDI 2021

Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK

Auteurs: Luca Nannini, Agathe Balayn, Adam Leon Smith
Publié dans: 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023, Page(s) 1198-1212
Éditeur: ACM
DOI: 10.1145/3593013.3594074

Toward Natural Language Mitigation Strategies for Cognitive Biases in Recommender Systems

Auteurs: Alisa Rieger, Mariet Theune, Nava Tintarev
Publié dans: NL4XAI 20202nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020
Éditeur: Association for Computational Linguistics (ACL)

Explaining Bayesian Networks in Natural Language using Factor Arguments. Evaluation in the medical domain.

Auteurs: Jaime Sevilla; Nikolay Babakov; Ehud Reiter; Alberto Bugarín.
Publié dans: EXPLIMED - First Workshop on Explainable Artificial Intelligence for the medical domain (EXPLIMED), 2024
Éditeur: ECAI 2024
DOI: 10.5281/zenodo.14040523

Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models

Auteurs: Sivaprasad, Adarsa; Reiter, Ehud
Publié dans: Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), 2024, Page(s) 127-132
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2401.17511

A Framework for Analyzing Fairness, Accountability, Transparency and Ethics: A Use-case in Banking Services

Auteurs: Ettore Mariotti, Jose M. Alonso, Roberto Confalonieri
Publié dans: 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2021, Page(s) 1-6, ISBN 978-1-6654-4407-1
Éditeur: IEEE
DOI: 10.1109/fuzz45933.2021.9494481

Entity-Based Semantic Adequacy for Data-to-Text Generation

Auteurs: Juliette Faille, Albert Gatt and Claire Gardent
Publié dans: Findings of the Association for Computational Linguistics: EMNLP 2021, 2021, Page(s) 1530-1540
Éditeur: Association for Computational Linguistics

Enhancing and Evaluating the Grammatical Framework Approach to Logic-to-Text Generation

Auteurs: Eduardo Calò, Elze van der Werf, Albert Gatt, Kees van Deemter
Publié dans: Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), 2022
Éditeur: ACL
DOI: 10.18653/v1/2022.gem-1.13

General Boolean Formula Minimization with QBF Solvers

Auteurs: Calò, Eduardo; Levy, Jordi
Publié dans: CCIA 2023, Numéro 12, 2023
Éditeur: CCIA
DOI: 10.48550/arxiv.2303.06643

HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales

Auteurs: Michele Cafagna; Kees van Deemter; Albert Gatt
Publié dans: Proceedings of the 16th International Natural Language Generation Conference, Numéro 12, 2023, Page(s) 293–312
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.inlg-main.21

Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment

Auteurs: Sumit Srivastava, Mariët Theune, Alejandro Catala, Chris Reed
Publié dans: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, Numéro 28 June 2024, 2024, Page(s) 189 - 194, ISBN 979-8-4007-0466-6
Éditeur: ACM
DOI: 10.1145/3631700.3664868

Exploiting Peer Trust and Semantic Similarities in the Assignment Assessment Process

Auteurs: Jairo Alejandro Lefebre Lobaina, Carles Sierra, Athina Georgara,
Publié dans: 2024
Éditeur: SPRINGER
DOI: 10.5281/zenodo.14066237

A Confusion Matrix for Evaluating Feature Attribution Methods

Auteurs: Anna Arias-Duart; Ettore Mariotti; Dario Garcia-Gasulla; Jose Maria Alonso-Moral
Publié dans: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
Éditeur: IEEE
DOI: 10.1109/cvprw59228.2023.00380

Position: Machine Learning-powered Assessments of the EU Digital Services Act Aid Quantify Policy Impacts on Online Harms

Auteurs: Luca Nannini, Michele Maggini Joshua, Davide Bassi, Eleonora Bonel
Publié dans: Proceedings of Machine Learning Research, 2024
Éditeur: ICML 2024
DOI: 10.5281/zenodo.14041316

The Role of Lexical Alignment in Human Understanding of Explanations by Conversational Agents

Auteurs: Sumit Srivastava, Mariët Theune, Alejandro Catala
Publié dans: Proceedings of the 28th International Conference on Intelligent User Interfaces, Numéro 27 Mar 2023, 2024, Page(s) 423 - 435, ISBN 979-8-4007-0106-1
Éditeur: ACM
DOI: 10.1145/3581641.3584086

Exploring Lexical Alignment in a Price Bargain Chatbot

Auteurs: Zhenqi Zhao, Mariët Theune, Sumit Srivastava, Daniel Braun
Publié dans: ACM Conversational User Interfaces 2024, Numéro 08 July 2024, 2024, Page(s) Article No.: 40, Pages 1 - 7, ISBN 979-8-4007-0511-3
Éditeur: ACM
DOI: 10.1145/3640794.3665576

Searching for the Whole Truth: Harnessing the Power of Intellectual Humility to Boost Better Search on Debated Topics

Auteurs: Alisa Rieger; Frank Bredius; Nava Tintarev; Maria Soledad Pera
Publié dans: Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, Numéro 11, 2023, ISBN 9781450394222
Éditeur: Association for Computing Machinery
DOI: 10.1145/3544549.3585693

„Mann“ is to “Donna” as「国王」is to « Reine » Adapting the Analogy Task for Multilingual and Contextual Embeddings

Auteurs: Timothee Mickus, Eduardo Calò, Léo Jacqmin, Denis Paperno, Mathieu Constant
Publié dans: Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), 2023
Éditeur: ACL
DOI: 10.18653/v1/2023.starsem-1.25

Argumentation Theoretical Frameworks for Explainable Artificial Intelligence

Auteurs: M. H. Demollin, Q. Shaheen, K. Budzynska, C. Sierra
Publié dans: Proc. of 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI2020), 2020
Éditeur: ACL Anthology

Peer reviewed articles (11)

Exploring the balance between interpretability and performance with carefully designed constrainable Neural Additive Models

Auteurs: Ettore Mariotti; José María Alonso Moral; Albert Gatt
Publié dans: Information Fusion, Numéro Volume 99, November 2023, 101882, 2023, ISSN 1566-2535
Éditeur: Elsevier BV
DOI: 10.1016/j.inffus.2023.101882

Nudges to Mitigate Confirmation Bias during Web Search on Debated Topics: Support vs. Manipulation

Auteurs: Alisa Rieger, Tim Draws, Mariët Theune, Nava Tintarev
Publié dans: ACM Transactions on the Web, Numéro 18, 2024, Page(s) 1-27, ISSN 1559-1131
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3635034

Mapping the landscape of ethical considerations in explainable AI research

Auteurs: Luca Nannini, Marta Marchiori Manerba & Isacco Beretta
Publié dans: Springer Ethics and Information Technology, Numéro Volume 26, article number 44, (2024), 2024, ISSN 1572-8439
Éditeur: Springer Link
DOI: 10.1007/s10676-024-09773-7

An explanation-oriented inquiry dialogue game for expert collaborative recommendations

Auteurs: Qurat-ul-ain Shaheen, Katarzyna Budzynska, Carles Sierra
Publié dans: Argument & Computation, 2024, Page(s) 1-36, ISSN 1946-2166
Éditeur: Taylor & Francis
DOI: 10.3233/aac-230010

Beyond phase-in: assessing impacts on disinformation of the EU Digital Services Act

Auteurs: Luca Nannini, Eleonora Bonel, Davide Bassi, Michele Joshua Maggini
Publié dans: AI and Ethics, 2024, ISSN 2730-5953
Éditeur: SPRINGER Nature
DOI: 10.1007/s43681-024-00467-w

Interpreting vision and language generative models with semantic visual priors

Auteurs: Michele Cafagna; Lina M. Rojas-Barahona; Kees van Deemter; Albert Gatt
Publié dans: Frontiers in Artificial Intelligence, Numéro 6, 2023, ISSN 2624-8212
Éditeur: Frontiers in Artificial Intelligence
DOI: 10.3389/frai.2023.1220476

Recommender systems under European AI regulations

Auteurs: Tommaso Di Noia, Nava Tintarev, Panagiota Fatourou, Markus Schedl
Publié dans: Communication of the ACM, 2022, ISSN 0001-0782
Éditeur: Association for Computing Machinary, Inc.
DOI: 10.1145/3512728

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

Auteurs: Kesen, Ilker; Pedrotti, Andrea; Dogan, Mustafa; Cafagna, Michele; Acikgoz, Emre Can; Parcalabescu, Letitia; Calixto, Iacer; Frank, Anette; Gatt, Albert; Erdem, Aykut; Erdem, Erkut
Publié dans: The Twelfth International Conference on Learning Representations (ICLR24),, Numéro 15, 2024, ISSN 2835-8856
Éditeur: OpenReview
DOI: 10.48550/arxiv.2311.07022

TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing

Auteurs: Ettore Mariotti, Arias Duart Anna, Michele Cafagna, Albert Gatt, Dario Garcia-Gasulla, Maria Jose Alonso
Publié dans: IEEE Access, 2024, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2024.3408062

Quantitative and Qualitative Analysis of Moral Foundations in Argumentation

Auteurs: Alina Landowska, Katarzyna Budzynska, He Zhang
Publié dans: Argumentation, Numéro 38, 2024, Page(s) 405-434, ISSN 0920-427X
Éditeur: D. Reidel Pub. Co.
DOI: 10.1007/s10503-024-09636-x

Measuring and implementing lexical alignment: A systematic literature review

Auteurs: Sumit Srivastava, Suzanna Wentzel, Alejandro Catala, Mariët Theune
Publié dans: Computer Speech & Language, Numéro 90, 2025, ISSN 0885-2308
Éditeur: Academic Press
DOI: 10.1016/j.csl.2024.101731

Thesis and dissertations (5)

Striving for Responsible Opinion Formation in Web Search on Debated Topics

Auteurs: Rieger, Alisa
Publié dans: 2024, ISBN 978-94-6366-941-2
Éditeur: TU Delft
DOI: 10.4233/uuid:703a1aad-d585-459a-b0b3-ac55d9e98fcd

Explainability in Process Mining: A Framework for Improved Decision-Making

Auteurs: Luca Nannini
Publié dans: 2024
Éditeur: Universidade de Santiago de Compostela (USC)
DOI: 10.5281/zenodo.14162735

Visually Grounded Language Generation: Data, Models and Explanations beyond Descriptive Captions

Auteurs: Cafagna, Michele
Publié dans: Numéro 12, 2024
Éditeur: University of Malta
DOI: 10.5281/zenodo.14052376

A holistic perspective on designing and evaluating explainable AI models: from white-box additive models to post-hoc explanations for black-box models

Auteurs: Ettore Mariotti
Publié dans: 2024
Éditeur: Universidade de Santiago de Compostela (USC)

Data Based Natural Language Generation: Evaluation and Explanability

Auteurs: Juliette Faille
Publié dans: 2023
Éditeur: Universite de Lorraine
DOI: 10.5281/zenodo.14231559

Other (4)

Ethos and Pathos in Online Group Discussions: Corpora for Polarisation Issues in Social Media

Auteurs: Gajewska, E., Budzynska, K., Konat, B., Koszowy, M., Kiljan, K., Uberna, M., & Zhang, H.
Publié dans: arXiv preprint arXiv:2404.04889, 2024
Éditeur: arxiv
DOI: 10.48550/arxiv.2404.04889

Linguistically Analysing Polarisation on Social Media

Auteurs: Ewelina Gajewska, Katarzyna Budzynska, Barbara Konat, Marcin Koszowy, Eds.
Publié dans: The New Ethos Reports, Numéro vol .1, 2023, Page(s) 1-32
Éditeur: Warsaw University of Technology
DOI: 10.17388/wut.2023.0001.ains

Scalability of Bayesian Network Structure Elicitation with Large Language Models: a Novel Methodology and Comparative Analysis

Auteurs: Nikolay Babakov, Ehud Reiter, Alberto Bugarin
Publié dans: 2024
Éditeur: Preprint-ACL Rolling Review
DOI: 10.5281/zenodo.14046261

Does Explainable AI Have Moral Value?

Auteurs: Brand, Joshua L. M.; Nannini, Luca
Publié dans: Numéro 12, 2023
Éditeur: Arxiv
DOI: 10.48550/arxiv.2311.14687

Book chapters (4)

Responsible Opinion Formation on Debated Topics in Web Search

Auteurs: Alisa Rieger, Tim Draws, Nicolas Mattis, David Maxwell, David Elsweiler, Ujwal Gadiraju, Dana McKay, Alessandro Bozzon, Maria Soledad Pera
Publié dans: Lecture Notes in Computer Science, Advances in Information Retrieval, 2024, Page(s) 437-465
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-56066-8_32

Examining Lexical Alignment in Human-Agent Conversations with GPT-3.5 and GPT-4 Models

Auteurs: Boxuan Wang, Mariët Theune, Sumit Srivastava
Publié dans: Lecture Notes in Computer Science, Chatbot Research and Design, Numéro 13 March 2024, 2024, Page(s) 94-114, ISBN 978-3-031-54975-5
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-54975-5_6

Evaluation of Human-Understandability of Global Model Explanations Using Decision Tree

Auteurs: Adarsa Sivaprasad, Ehud Reiter, Nava Tintarev, Nir Oren
Publié dans: Communications in Computer and Information Science, Artificial Intelligence. ECAI 2023 International Workshops, 2024, Page(s) 43-65
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-50396-2_3

VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena

Auteurs: Parcalabescu, L; Cafagna, M; Muradjan, L; Frank, A; Calixto, I; Gatt, A; Afd Intelligent Software Systems; Sub Natural Language Processing; Natural Language Processing
Publié dans: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL'22). Association for Computational Linguistics, Numéro 21, 2022, Page(s) 8253–8280
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2022.acl-long.567