A distributional MOdel of Reference to Entities

Informations projet

AMORE

N° de convention de subvention: 715154

DOI

10.3030/715154

Projet clôturé

Date de signature de la CE 4 Novembre 2016

Date de début 1 Février 2017

Date de fin 31 Janvier 2023

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 499 805,00

Contribution de l’UE

€ 1 499 805,00

Coordonné par

UNIVERSIDAD POMPEU FABRA
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 .

Publications

Conference proceedings (34)

Implying or implicating not both in declaratives and interrogatives

Auteurs: Matthijs Westera
Publié dans: Proceedings of Sinn und Bedeutung, Numéro 24(2), 2020, Page(s) 423-438
Éditeur: Osnabrück University and Humboldt University of Berlin
DOI: 10.18148/sub/2020.v24i2.906

Quantifying informativeness of names in visual space.

Auteurs: Gualdoni Eleonora, Kemp Charles, Xu Yang, Boleda Gemma
Publié dans: Proceedings of the 45th Annual Conference of the Cognitive Science Society (CogSci 2023), 2023
Éditeur: Cognitive Science Society
DOI: 10.31234/osf.io/rxw9b

Effects of task and visual context on referring expressions using natural scenes

Auteurs: Mädebach, A., E. Gualdoni, E. Torubarova, G. Boleda.
Publié dans: Proceedings of CogSci, 2022
Éditeur: Cognitive Science Society
DOI: 10.31234/osf.io/fyzsk

TED-Q: TED Talks and the Questions they Evoke

Auteurs: Matthijs Westera, Laia Mayol, Hannah Rohde
Publié dans: Proceedings of the 12th Language Resources and Evaluation Conference, 2020, Page(s) 1118-1127
Éditeur: European Language Resources Association

A closer look at scalar diversity using contextualized semantic similarity

Auteurs: Matthijs Westera, Gemma Boleda
Publié dans: Proceedings of Sinn Und Bedeutung, Numéro 24(2), 2020, Page(s) 439-454
Éditeur: Osnabrück University/Humboldt University
DOI: 10.18148/sub/2020.v24i2.908

Woman or tennis player? Visual typicality and lexical frequency affect variation in object naming.

Auteurs: Gualdoni, E., A. Mädebach, T. Brochhagen, G. Boleda
Publié dans: Proceedings of CogSci, 2022
Éditeur: Cognitive Science Society
DOI: 10.31234/osf.io/34ckf

Communication breakdown: on the low mutual intelligibility between human and neural captioning

Auteurs: Dessì R, Gualdoni E, Franzon F, Boleda G, Baroni M.
Publié dans: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Éditeur: ACL
DOI: 10.48550/arxiv.2210.11512

Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions

Auteurs: Matthijs Westera, Jacopo Amidei, Laia Mayol
Publié dans: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 5004-5012
Éditeur: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.439

The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation

Auteurs: Aina, L., Linzen, T.
Publié dans: Proc. BlackboxNLP 2021: Analyzing and Interpreting Neural Networks for NLP., 2021
Éditeur: ACL
DOI: 10.18653/v1/2021.blackboxnlp-1.4

Cross-domain image captioning with discriminative finetuning.

Auteurs: Dessì R, Bevilacqua M, Gualdoni E, Rakotonirina N, Franzon F, Baroni M.
Publié dans: Proceedings of The Thirty-Fourth IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Éditeur: IEEE
DOI: 10.48550/arxiv.2304.01662

Run Like a Girl! Sport-Related Gender Bias in Language and Vision

Auteurs: Sophia Harrison, Eleonora Gualdoni, Gemma Boleda
Publié dans: Findings of ACL, 2023
Éditeur: ACL
DOI: 10.48550/arxiv.2305.14468

Westera, Matthijs, and Hannah Rohde

Auteurs: Asking between the lines: Elicitation of evoked questions in text.
Publié dans: Proceedings of the 22nd Amsterdam Colloquium, 2019
Éditeur: Julian J. Schlo ̈der, Dean McHugh & Floris Roelofsen

Challenges in including extra-linguistic context in pre-trained language models.

Auteurs: Sorodoc, I., L. Aina, G. Boleda
Publié dans: Proceedings of the Third Workshop on Insights from Negative Results in NLP, 2022
Éditeur: ACL
DOI: 10.18653/v1/2022.insights-1.18

AMORE-UPF at SemEval-2018 Task 4: BiLSTM with Entity Library

Auteurs: Aina, Laura; Silberer, Carina; Sorodoc, Ionut-Teodor; Westera, Matthijs; Boleda, Gemma
Publié dans: Proceedings of The 12th International Workshop on Semantic Evaluation, Numéro 1, 2018
Éditeur: Association for Computational Linguistics

Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision

Auteurs: Pezzelle, Sandro; Sorodoc, Ionut-Teodor; Bernardi, Raffaella
Publié dans: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018, Page(s) 419-430
Éditeur: Association for Computational Linguistics

Living a discrete life in a continuous world: Reference with distributed representations

Auteurs: Boleda, Gemma; Padó, Sebastian; Pham, Nghia The; Baroni, Marco
Publié dans: Proceedings of the 12th International Conference on Computational Semantics — Short papers, 2017
Éditeur: Association for Computational Linguistics

Instances and concepts in distributional space

Auteurs: Gemma Boleda, Abhijeet Gupta, Sebastian Padó
Publié dans: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 2017, Page(s) 79-85
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/e17-2013

Questions Under Discussion, brevity, and the asymmetry of alternatives

Auteurs: Matthijs Westera
Publié dans: Proceedings of the 21st Amsterdam Colloquium, Numéro 21, 2017, Page(s) 502-510
Éditeur: Institute for Logic, Language and Computation, University of Amsterdam

Grounding Semantic Roles in Images

Auteurs: Carina Silberer, Manfred Pinkal
Publié dans: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, Page(s) 2616-2626
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/d18-1282

How to represent a word and predict it, too: Improving tied architectures for language modelling

Auteurs: Kristina Gulordava, Laura Aina, Gemma Boleda
Publié dans: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, Page(s) 2936-2941
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/d18-1323

Don't blame distributional semantics if it can't do entailment

Auteurs: Matthijs Westera, Gemma Boleda
Publié dans: Proceedings of the 13th International Conference on Computational Semantics - Long Papers, 2019
Éditeur: Association for Computational Linguistics

A distributional study of negated adjectives and antonyms

Auteurs: Laura Aina, Rafaella Bernardi, Raquel Fernández
Publié dans: Proceedings of the 5th Italian Conference on Computational Linguistics (CLiC-it 2018), Numéro Vol-2253, 2018
Éditeur: Elena Cabrio, Alessandro Mazzei, Fabio Tamburini

Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible

Auteurs: Abhijeet Gupta, Gemma Boleda, Sebastian Padó
Publié dans: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), 2017, Page(s) 104-109
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/s17-1012

What do Entity-Centric Models Learn? Insights from Entity Linking in Multi-Party Dialogue

Auteurs: Laura Aina, Carina Silberer, Ionut-Teodor Sorodoc, Matthijs Westera, Gemma Boleda
Publié dans: Proceedings of the 2019 Conference of the North, 2019, Page(s) 3772-3783
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/n19-1378

Short-Term Meaning Shift: A Distributional Exploration

Auteurs: Marco Del Tredici, Raquel Fernández, Gemma Boleda
Publié dans: Proceedings of the 2019 Conference of the North, 2019, Page(s) 2069-2075
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/n19-1210

Putting Words in Context: LSTM Language Models and Lexical Ambiguity

Auteurs: Laura Aina, Kristina Gulordava, Gemma Boleda
Publié dans: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, Page(s) 3342-3348
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1324

Recurrent Instance Segmentation using Sequences of Referring Expressions

Auteurs: Alba Maria Hererra-Palacio,Carles Ventura,Carina Silberer,Ionut-Teodor Sorodoc,Gemma Boleda,Xavier Giro-i-Nieto
Publié dans: 2019
Éditeur: NeurIPS

Humans Meet Models on Object Naming: A New Dataset and Analysis

Auteurs: Carina Silberer, Sina Zarrieß, Matthijs Westera, Gemma Boleda
Publié dans: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 1893-1905
Éditeur: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.172

Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks

Auteurs: Kristina Gulordava, Thomas Brochhagen, Gemma Boleda
Publié dans: Proceedings of the 42nd Annual Conference of the Cognitive Science Society, Numéro 42, 2020, Page(s) 2089-2095
Éditeur: Cognitive Science Society

Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution

Auteurs: Laura Aina, Xixian Liao, Gemma Boleda, and Matthijs Westera
Publié dans: Proceedings of the 25th Conference on Computational Natural Language Learning, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.conll-1.36

Controlled tasks for model analysis: Retrieving discrete information from sequences

Auteurs: Ionut-Teodor Sorodoc, Gemma Boleda, and Marco Baroni
Publié dans: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.blackboxnlp-1.37

Probing for Referential Information in Language Models

Auteurs: Ionut-Teodor Sorodoc, Kristina Gulordava, Gemma Boleda
Publié dans: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Page(s) 4177-4189
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.384

Object Naming in Language and Vision: A Survey and a New Dataset

Auteurs: Carina Silberer, Sina Zarrieß, Gemma Boleda
Publié dans: Proceedings of the 12th Language Resources and Evaluation Conference, 2020, Page(s) 5792–5801
Éditeur: European Language Resources Association

Modeling word interpretation with deep language models: The interaction between expectations and lexical information

Auteurs: Laura Aina, Thomas Brochhagen, Gemma Boleda
Publié dans: Proceedings of the 42nd Annual Conference of the Cognitive Science Society, Numéro 42, 2020, Page(s) 1518-1524
Éditeur: Cognitive Science Society

Peer reviewed articles (9)

Brief at the Risk of Being Misunderstood: Consolidating Population- and Individual-Level Tendencies

Auteurs: Thomas Brochhagen
Publié dans: Computational Brain & Behavior, Numéro 4/3, 2021, Page(s) 305-317, ISSN 2522-0861
Éditeur: Springer Nature
DOI: 10.1007/s42113-021-00099-x

Distributional Semantics and Linguistic Theory

Auteurs: Gemma Boleda
Publié dans: Annual Review of Linguistics, Numéro 6/1, 2020, Page(s) 213-234, ISSN 2333-9683
Éditeur: Annual Reviews
DOI: 10.1146/annurev-linguistics-011619-030303

Distributional Models of Category Concepts Based on Names of Category Members

Auteurs: Matthijs Westera, Abhijeet Gupta, Gemma Boleda, Sebastian Padó
Publié dans: Cognitive Science, Numéro 45/9, 2021, ISSN 0364-0213
Éditeur: Lawrence Erlbaum Associates Inc.
DOI: 10.1111/cogs.13029

Attentional pragmatics: A pragmatic approach to exhaustivity.

Auteurs: Westera, Matthijs
Publié dans: Semantics and Pragmatics, 2022, ISSN 1937-8912
Éditeur: Linguistic Society of America
DOI: 10.3765/sp.15.10

"Hearing ""Birch"" Hampers Saying ""Duck""-An Event-Related Potential Study on Phonological Interference in Immediate and Delayed Word Production"

Auteurs: Andreas Mädebach, Andreas Widmann, Melina Posch, Erich Schröger, Jörg D. Jescheniak
Publié dans: Journal of Cognitive Neuroscience, 2022, ISSN 0898-929X
Éditeur: Cambridge Center for Behavioral Studies
DOI: 10.1162/jocn_a_01859

Rising declaratives of the Quality-suspending kind

Auteurs: Matthijs Westera
Publié dans: Glossa: a journal of general linguistics, Numéro 3/1, 2018, ISSN 2397-1835
Éditeur: Ubiquity Press
DOI: 10.5334/gjgl.415

Idioms and the syntax/semantics interface of descriptive content vs. reference

Auteurs: Berit Gehrke, Louise McNally
Publié dans: Linguistics, Numéro 57/4, 2019, Page(s) 769-814, ISSN 0024-3949
Éditeur: Mouton de Gruyter
DOI: 10.1515/ling-2019-0016

When do languages use the same word for different meanings? The Goldilocks principle in colexification

Auteurs: Thomas Brochhagen & Gemma Boleda
Publié dans: Cognition, 2022, ISSN 0010-0277
Éditeur: Elsevier BV
DOI: 10.1016/j.cognition.2022.105179

Negated Adjectives and Antonyms in Distributional Semantics: not similar?

Auteurs: Laura Aina, Raffaella Bernardi, Raquel Fernández
Publié dans: Italian Journal of Computational Linguistics, Numéro 5/1, 2019, Page(s) 57-71, ISSN 2499-4553
Éditeur: Lexis Compagnia Editoriale
DOI: 10.4000/ijcol.457

Book chapters (2)

Conceptual Versus Referential Affordance in Concept Composition

Auteurs: Louise McNally, Gemma Boleda
Publié dans: Compositionality and Concepts, 2017, Page(s) 245-267
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-45977-6_10

“Show Me the Cup”: Reference with Continuous Representations

Auteurs: Marco Baroni, Gemma Boleda, Sebastian Padó
Publié dans: Computational Linguistics and Intelligent Text Processing - 18th International Conference, CICLing 2017, Budapest, Hungary, April 17–23, 2017, Revised Selected Papers, Part I, Numéro 10761, 2018, Page(s) 209-224, ISBN 978-3-319-77112-0
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-77113-7_17