no code implementations • RANLP 2021 • Jordi Armengol-Estapé, Marta R. Costa-jussà, Carlos Escolano
Introducing factors, that is to say, word features such as linguistic information referring to the source tokens, is known to improve the results of neural machine translation systems in certain settings, typically in recurrent architectures.
1 code implementation • 21 Dec 2020 • Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marta Villegas
Email can be one of the most fruitful attack vectors of research institutions as they also contain access to all accounts and thus to all private information.
Cryptography and Security Social and Information Networks
1 code implementation • NeurIPS 2021 • David Pérez-Fernández, Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marta Villegas
Characterizing the structural properties of neural networks is crucial yet poorly understood, and there are no well-established similarity measures between networks.
no code implementations • 25 Feb 2021 • Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Casimiro Pio Carrino, Ona de Gibert, Aitor Gonzalez-Agirre, Marta Villegas
We computed both Word and Sub-word Embeddings using FastText.
1 code implementation • NeurIPS 2021 • Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé, Marta Villegas
The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model.
2 code implementations • 15 Jul 2021 • Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marc Pàmies, Joan Llop-Palao, Joaquín Silveira-Ocampo, Casimiro Pio Carrino, Aitor Gonzalez-Agirre, Carme Armentano-Oller, Carlos Rodriguez-Penagos, Marta Villegas
This work presents MarIA, a family of Spanish language models and associated resources made available to the industry and the research community.
no code implementations • Findings (ACL) 2021 • Jordi Armengol-Estapé, Casimiro Pio Carrino, Carlos Rodriguez-Penagos, Ona de Gibert Bonet, Carme Armentano-Oller, Aitor Gonzalez-Agirre, Maite Melero, Marta Villegas
For this, we: (1) build a clean, high-quality textual Catalan corpus (CaText), the largest to date (but only a fraction of the usual size of the previous work in monolingual language models), (2) train a Transformer-based language model for Catalan (BERTa), and (3) devise a thorough evaluation in a diversity of settings, comprising a complete array of downstream tasks, namely, Part of Speech Tagging, Named Entity Recognition and Classification, Text Classification, Question Answering, and Semantic Textual Similarity, with most of the corresponding datasets being created ex novo.
1 code implementation • NeurIPS Workshop AIPLANS 2021 • Jordi Armengol-Estapé, Michael F. P. O'Boyle
Deep learning has had a significant impact on many fields.
2 code implementations • LREC 2022 • Jordi Armengol-Estapé, Ona de Gibert Bonet, Maite Melero
Generative Pre-trained Transformers (GPTs) have recently been scaled to unprecedented sizes in the history of machine learning.
no code implementations • 8 Sep 2021 • Casimiro Pio Carrino, Jordi Armengol-Estapé, Asier Gutiérrez-Fandiño, Joan Llop-Palao, Marc Pàmies, Aitor Gonzalez-Agirre, Marta Villegas
To the best of our knowledge, we provide the first biomedical and clinical transformer-based pretrained language models for Spanish, intending to boost native Spanish NLP applications in biomedicine.
no code implementations • 16 Sep 2021 • Casimiro Pio Carrino, Jordi Armengol-Estapé, Ona de Gibert Bonet, Asier Gutiérrez-Fandiño, Aitor Gonzalez-Agirre, Martin Krallinger, Marta Villegas
We introduce CoWeSe (the Corpus Web Salud Espa\~nol), the largest Spanish biomedical corpus to date, consisting of 4. 5GB (about 750M tokens) of clean plain text.
1 code implementation • 23 Oct 2021 • Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Aitor Gonzalez-Agirre, Marta Villegas
There are many Language Models for the English language according to its worldwide relevance.
1 code implementation • 31 Oct 2021 • Asier Gutiérrez-Fandiño, Miquel Noguer i Alonso, Petter Kolm, Jordi Armengol-Estapé
We introduce a new language representation model in finance called Financial Embedding Analysis of Sentiment (FinEAS).
1 code implementation • 10 Dec 2021 • Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé
In this work, we present the Large Labelled Logo Dataset (L3D), a multipurpose, hand-labelled, continuously growing dataset.
Ranked #1 on Image Classification on Large Labelled Logo Dataset (L3D) (Eval F1 metric)
1 code implementation • 14 Feb 2022 • Ona de Gibert, Ksenia Kharitonova, Blanca Calvo Figueras, Jordi Armengol-Estapé, Maite Melero
In this work, we introduce sequence-to-sequence language resources for Catalan, a moderately under-resourced language, towards two tasks, namely: Summarization and Machine Translation (MT).
no code implementations • 30 Jun 2022 • Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé, David Griol, Zoraida Callejas
However, the results in Spanish present important shortcomings, as they are either too small in comparison with other languages, or present a low quality derived from sub-optimal cleaning and deduplication.
no code implementations • 21 May 2023 • Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins, Michael F. P. O'Boyle
SLaDe is up to 6 times more accurate than Ghidra, a state-of-the-art, industrial-strength decompiler and up to 4 times more accurate than the large language model ChatGPT and generates significantly more readable code than both.
no code implementations • 1 Apr 2024 • Jordi Armengol-Estapé, Rodrigo C. O. Rocha, Jackson Woodruff, Pasquale Minervini, Michael F. P. O'Boyle
The escalating demand to migrate legacy software across different Instruction Set Architectures (ISAs) has driven the development of assembly-to-assembly translators to map between their respective assembly languages.
1 code implementation • WMT (EMNLP) 2021 • Ksenia Kharitonova, Ona de Gibert Bonet, Jordi Armengol-Estapé, Mar Rodriguez i Alvarez, Maite Melero
This paper describes the participation of the BSC team in the WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task.
1 code implementation • BioNLP (ACL) 2022 • Casimiro Pio Carrino, Joan Llop, Marc Pàmies, Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Joaquín Silveira-Ocampo, Alfonso Valencia, Aitor Gonzalez-Agirre, Marta Villegas
This work presents the first large-scale biomedical Spanish language models trained from scratch, using large biomedical corpora consisting of a total of 1. 1B tokens and an EHR corpus of 95M tokens.
no code implementations • LREC 2022 • Ona de Gibert Bonet, Iakes Goenaga, Jordi Armengol-Estapé, Olatz Perez-de-Viñaspre, Carla Parra Escartín, Marina Sanchez, Mārcis Pinnis, Gorka Labaka, Maite Melero
In this work, we present the work that has been carried on in the MT4All CEF project and the resources that it has generated by leveraging recent research carried out in the field of unsupervised learning.
no code implementations • SIGUL (LREC) 2022 • Ona de Gibert Bonet, Ksenia Kharitonova, Blanca Calvo Figueras, Jordi Armengol-Estapé, Maite Melero
In this work, we make the case of quality over quantity when training a MT system for a medium-to-low-resource language pair, namely Catalan-English.