On 03.06.21 we had our virtual kick-off meeting where we discussed the future of ENRICH4ALL. In the following picture you see most of the partners, stay tuned!
ENRICH4ALL was presented at the Belgian-Luxembourgish workshop in the frames of the European Language Grid project on 08.07.2021. The workshop was collocated with the CLIN workshop and was organised by Prof. Walter Daelemans and Dr. Dimitra Anastasiou. The presentations of the speakers can be found here.
ENRICH4ALL was presented as poster/demo at the 33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning (BNAIC/BENELEARN 2021). This is a joint conference by the University of Luxembourg, under the auspices of the Faculty of Science, Technology, and Medicine (FSTM) and the Interdisciplinary Lab for Intelligent and Adaptive Systems (ILIAS), and the IT for Innovative Services (ITIS) research department from the Luxembourg Institute of Science and Technology.
The paper is available at the conference pre-proceedings.
ENRICH4ALL is presented as poster at the 23rd Annual Conference of the European Association for Machine Translation, June 1 - 3, Ghent, Belgium.
Proceedings: Lieve Macken, Andrew Rufener, Joachim Van den Bogaert, Joke Daems, Arda Tezcan, Bram Vanroy, Margot Fonteyne, Loïc Barrault, Marta R. Costa-jussà, Ellie Kemp, Spyridon Pilos, Christophe Declercq, Maarit Koponen, Mikel L. Forcada, Carolina Scarton, Helena Moniz. 2022. Proceedings of the 23rd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Ghent, Belgium. Retrieved from https://lt3.ugent.be/media/uploads/eamt2022/proceedings-eamt2022.pdf.
The project ENRICH4ALL will be presented at a post-Conference Workshop of LREC 2022 in Marseille (FR), 24-25 June 2022. The 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages (SIGUL 2022) will provide a forum for the presentation and discussion of cutting-edge research in text and speech processing for under-resourced languages by academic and industry researchers.
This paper presents an open-domain Question Answering system for Romanian, answering COVID-19 related questions. The QA system pipeline involves automatic question processing, automatic query generation, web searching for the top 10 most relevant documents and answer extraction using a fine-tuned BERT model for Extractive QA, trained on a COVID-19 data set that we have manually created. The paper will present the QA system and its integration with the Romanian language technologies portal RELATE, the COVID-19 data set and different evaluations of the QA performance.