IMAGINE – Informing Multi-modal lAnguage Generation wIth world kNowledgE

Información del proyecto

IMAGINE

Identificador del acuerdo de subvención: 838188

DOI 10.3030/838188

Proyecto cerrado

Fecha de la firma de la CE 27 Marzo 2019

Fecha de inicio 14 Junio 2019

Fecha de finalización 23 Abril 2022

Financiado con arreglo a

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Coste total € 232 393,92

Aportación de la UE € 232 393,92

Coordinado por

UNIVERSITEIT VAN AMSTERDAM
Netherlands

Publicaciones

Conference proceedings (8)

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

Autores: 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
Publicado en: Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, Edición 1-3 June, 2022, Página(s) 347-348
Editor: European Association for Machine Translation

Latent Variable Model for Multi-modal Translation

Autores: Iacer Calixto, Miguel Rios, Wilker Aziz
Publicado en: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Edición July 2019, 2019, Página(s) 6392–6405
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1642

Can Wikipedia Categories Improve Masked Language Model Pretraining?

Autores: Diksha Meghwal, Katharina Kann, Iacer Calixto, Stanislaw Jastrzebski
Publicado en: Proceedings of the The Fourth Widening Natural Language Processing Workshop, 2020, Página(s) 78-78
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.winlp-1.19

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

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

Are Scene Graphs Good Enough to Improve Image Captioning?

Autores: Victor Siemen Janusz Milewski, Marie-Francine Moens, Iacer Calixto
Publicado en: 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, Edición Dec.2020, 2020, Página(s) 504–515
Editor: Association for Computational Linguistics

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

Autores: Letitia Parcalabescu, Albert Gatt, Anette Frank and Iacer Calixto
Publicado en: Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR), 2021
Editor: Association for Computational Linguistics

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

Autores: Jason Phang, Iacer Calixto, Phu Mon Htut, Yada Pruksachatkun, Haokun Liu, Clara Vania, Katharina Kann, Samuel R. Bowman
Publicado en: 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, Edición Dec.2020, 2020, Página(s) 557–575
Editor: Association for Computational Linguistics

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

Autores: Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, Albert Gatt.
Publicado en: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022
Editor: Association for Computational Linguistics

Other (1)

Endowing Language Models with Multimodal Knowledge Graph Representations

Autores: Ningyuan (Teresa) Huang,Yash R. Deshpande,Yibo Liu,Houda Alberts,Kyunghyun Cho,Clara Vania,Iacer Calixto
Publicado en: Arxiv, Edición 27/06/2022, 2022
Editor: Arxiv