IMAGINE – Informing Multi-modal lAnguage Generation wIth world kNowledgE

Informacje na temat projektu

IMAGINE

Identyfikator umowy o grant: 838188

DOI 10.3030/838188

Projekt został zamknięty

Data podpisania przez KE 27 Marca 2019

Data rozpoczęcia 14 Czerwca 2019

Data zakończenia 23 Kwietnia 2022

Finansowanie w ramach

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Koszt całkowity € 232 393,92

Wkład UE € 232 393,92

Koordynowany przez

UNIVERSITEIT VAN AMSTERDAM
Netherlands

Publikacje

Conference proceedings (8)

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

Autorzy: 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
Opublikowane w: Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, Numer 1-3 June, 2022, Strona(/y) 347-348
Wydawca: European Association for Machine Translation

Latent Variable Model for Multi-modal Translation

Autorzy: Iacer Calixto, Miguel Rios, Wilker Aziz
Opublikowane w: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Numer July 2019, 2019, Strona(/y) 6392–6405
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1642

Can Wikipedia Categories Improve Masked Language Model Pretraining?

Autorzy: Diksha Meghwal, Katharina Kann, Iacer Calixto, Stanislaw Jastrzebski
Opublikowane w: Proceedings of the The Fourth Widening Natural Language Processing Workshop, 2020, Strona(/y) 78-78
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.winlp-1.19

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

Autorzy: Alberts, Houda; Huang, Teresa; Deshpande, Yash; Liu, Yibo; Cho, Kyunghyun; Vania, Clara; Calixto, Iacer
Opublikowane w: Proceedings of the 1st Workshop on Multilingual Representation Learning, 2021, Strona(/y) 138–152
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2021.mrl-1.13

Are Scene Graphs Good Enough to Improve Image Captioning?

Autorzy: Victor Siemen Janusz Milewski, Marie-Francine Moens, Iacer Calixto
Opublikowane w: 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, Numer Dec.2020, 2020, Strona(/y) 504–515
Wydawca: Association for Computational Linguistics

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

Autorzy: Letitia Parcalabescu, Albert Gatt, Anette Frank and Iacer Calixto
Opublikowane w: Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR), 2021
Wydawca: Association for Computational Linguistics

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

Autorzy: Jason Phang, Iacer Calixto, Phu Mon Htut, Yada Pruksachatkun, Haokun Liu, Clara Vania, Katharina Kann, Samuel R. Bowman
Opublikowane w: 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, Numer Dec.2020, 2020, Strona(/y) 557–575
Wydawca: Association for Computational Linguistics

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

Autorzy: Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, Albert Gatt.
Opublikowane w: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022
Wydawca: Association for Computational Linguistics

Other (1)

Endowing Language Models with Multimodal Knowledge Graph Representations

Autorzy: Ningyuan (Teresa) Huang,Yash R. Deshpande,Yibo Liu,Houda Alberts,Kyunghyun Cho,Clara Vania,Iacer Calixto
Opublikowane w: Arxiv, Numer 27/06/2022, 2022
Wydawca: Arxiv