IMAGINE – Informing Multi-modal lAnguage Generation wIth world kNowledgE

Informations projet

IMAGINE

N° de convention de subvention: 838188

DOI 10.3030/838188

Projet clôturé

Date de signature de la CE 27 Mars 2019

Date de début 14 Juin 2019

Date de fin 23 Avril 2022

Financé au titre de

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Coût total € 232 393,92

Contribution de l’UE € 232 393,92

Coordonné par

UNIVERSITEIT VAN AMSTERDAM
Netherlands

Publications

Conference proceedings (8)

Multi3Generation: Multi-task, Multilingual, Multi-Modal Language Generation.

Auteurs: Anabela Barreiro, José C. de Souza, Albert Gatt, Mehul Bhatt, Elena Lloret, Aykut Erdem, Dimitra Gkatzia, Helena Moniz, Irene Russo, Fabio Kepler, Iacer Calixto, Marcin Paprzycki, François Portet, Isabelle Augenstein, Mirela Alhasani
Publié dans: Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, Numéro 1-3 June, 2022, Page(s) 347-348
Éditeur: European Association for Machine Translation

Latent Variable Model for Multi-modal Translation

Auteurs: Iacer Calixto, Miguel Rios, Wilker Aziz
Publié dans: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Numéro July 2019, 2019, Page(s) 6392–6405
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1642

Can Wikipedia Categories Improve Masked Language Model Pretraining?

Auteurs: Diksha Meghwal, Katharina Kann, Iacer Calixto, Stanislaw Jastrzebski
Publié dans: Proceedings of the The Fourth Widening Natural Language Processing Workshop, 2020, Page(s) 78-78
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.winlp-1.19

VisualSem: a high-quality knowledge graph for vision and language

Auteurs: Alberts, Houda; Huang, Teresa; Deshpande, Yash; Liu, Yibo; Cho, Kyunghyun; Vania, Clara; Calixto, Iacer
Publié dans: Proceedings of the 1st Workshop on Multilingual Representation Learning, 2021, Page(s) 138–152
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.mrl-1.13

Are Scene Graphs Good Enough to Improve Image Captioning?

Auteurs: Victor Siemen Janusz Milewski, Marie-Francine Moens, Iacer Calixto
Publié dans: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, Numéro Dec.2020, 2020, Page(s) 504–515
Éditeur: Association for Computational Linguistics

Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks

Auteurs: Letitia Parcalabescu, Albert Gatt, Anette Frank and Iacer Calixto
Publié dans: Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR), 2021
Éditeur: Association for Computational Linguistics

English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too

Auteurs: Jason Phang, Iacer Calixto, Phu Mon Htut, Yada Pruksachatkun, Haokun Liu, Clara Vania, Katharina Kann, Samuel R. Bowman
Publié dans: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, Numéro Dec.2020, 2020, Page(s) 557–575
Éditeur: Association for Computational Linguistics

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

Auteurs: Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, Albert Gatt.
Publié dans: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022
Éditeur: Association for Computational Linguistics

Other (1)

Endowing Language Models with Multimodal Knowledge Graph Representations

Auteurs: Ningyuan (Teresa) Huang,Yash R. Deshpande,Yibo Liu,Houda Alberts,Kyunghyun Cho,Clara Vania,Iacer Calixto
Publié dans: Arxiv, Numéro 27/06/2022, 2022
Éditeur: Arxiv