Multi3Generation: Multitask, Multilingual, and Multimodal Language Generation

Elena Lloret; Anabela Barreiro; Mehul Bhatt; Alberto Bugarín-Diz; Gianfranco E Modoni; Max Silberztein; Iacer Calixto; Grazina Korvel; Konstantinos Diamantaras; Alkiviadis Katsalis; Oleskii Turuta; Irene Russo; Aykut Erdem

doi:10.12688/openreseurope.16307.1

Multi3Generation: Multitask, Multilingual, and Multimodal Language Generation

Open Res Eur. 2023 Oct 12:3:176. doi: 10.12688/openreseurope.16307.1. eCollection 2023.

Authors

Affiliations

¹ University of Alicante, Alicante,, San Vicente del Raspeig, 03690, Spain.
² Instituto de Engenharia de Sistemas e Computadores: Investigac¸ao e Desenvolvimento (INESC-ID), Lisboa, Lisboa, Rua Alves Redol, 9, 1000-029, Portugal.
³ CoDesign Lab EU, Örebro University, Örebro, Örebro County, S-701 82, Sweden.
⁴ Centro Singular de Investigacion en Tecnolox´ıas Intelixentes (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Galicia, 15782, Spain.
⁵ Institute of Intelligent Industrial Systems and Technologies for Advanced Manufacturing, National Research Council, STIIMA CNR, Bari, via Lembo 38F, 70124, Italy.
⁶ Universite de Franche-Comte, Besançon, Bourgogne-Franche-Comté, 30-32, rue Megevand, 25030, France.
⁷ Amsterdam UMC, Department of Medical Informatics, Amsterdam Public RHealth Research Institute, Amsterdam, Meibergdreef 9, 1105 AZ, The Netherlands.
⁸ Amsterdam Public Health, Methodology and Mental Health, Amsterdam, North Holland, The Netherlands.
⁹ Vilnius University, Vilnius, Akademijos st. 4, 08412, Lithuania.
¹⁰ Department of Information and Electronic Engineering, International Hellenic University, Thesaloniki, 57400, Greece.
¹¹ Kharkiv National University of Radio Electronics, Ukraine, Nauky Ave, 14, 61166, Ukraine.
¹² ILC CNR "A. Zampolli", Pisa, Via G. Moruzzi, 1, 56124, Italy.
¹³ Koç University, Istanbul, Sarıyer, 34450 ˙, Turkey.

Abstract

The purpose of this article is to highlight the critical importance of language generation today. In particular, language generation is explored from the following three aspects: multi-modality, multilinguality, and multitask, which all of them play crucial role for Natural Language Generation (NLG) community. We present the activities conducted within the Multi3Generation COST Action (CA18231), as well as current trends and future perspectives for multitask, multilingual and multimodal language generation.

Keywords: Language Technologies; Multi-task; Multi3Generation; Multilinguality; Multimodality; Natural Language Generation.

Grants and funding

This project has received funding from the European Cooperation in Science and Technology (COST) under the agreement no. CA18231 - Multi3Generation: Multitask, Multilingual, Multimodal Language Generation. In addition, this research work is partially conducted within the R&D projects “CORTEX: Conscious Text Generation” (PID2021-123956OB-I00) partially funded by MCIN/ AEI/10.13039/501100011033/ and by “ERDF A way of making Europe” and “Enhancing the modernization public sector organizations by deploying Natural Language Processing to make their digital content CLEARER to those with cognitive disabilities” (TED2021-130707B-I00), funded by MCIN/AEI/10.13039/501100011033 and “European Union NextGenerationEU/PRTR”, and by the Generalitat Valenciana through the project “NL4DISMIS: Natural Language Technologies for dealing with dis- and misinformation with grant reference (CIPROM/2021/21)”, Project Counterfactual Commonsense (Örebro University), funded by the Swedish Research Council (VR).