Ponències/Comunicacions de congressos
Recent Submissions
-
Multiformer: a head-configurable transformer-based model for direct speech translation
(Association for Computational Linguistics, 2022)
Conference lecture
Open AccessTransformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries ... -
Evaluating gender bias in speech translation
(European Language Resources Association, 2022)
Conference lecture
Open AccessThe scientific community is increasingly aware of the necessity to embrace pluralism and consistently represent major and minor social groups. Currently, there are no standard evaluation techniques for different types of ... -
Attention weights in transformer NMT fail aligning words between sequences but largely explain model predictions
(Association for Computational Linguistics, 2021)
Conference lecture
Open AccessThis work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically ... -
On the locality of attention in direct speech translation
(Association for Computational Linguistics, 2022)
Conference lecture
Open AccessTransformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long ... -
High frequent in-domain word segmentation and forward translation for the WMT21 Biomedical task
(Association for Computational Linguistics, 2021)
Conference report
Open AccessThis paper reports the optimization of using the out-of-domain data in the Biomedical translation task. We firstly optimized our parallel training dataset using the BabelNet in-domain terminology words. Afterward, to ... -
Enhancing sequence-to-sequence modeling for RDF triples to natural text
(Association for Computational Linguistics, 2020)
Conference report
Open AccessEstablishes key guidelines on how, which and when Machine Translation (MT) techniques are worth applying to RDF-to-Text task. Not only do we apply and compare the most prominent MT architecture, the Transformer, but we ... -
The UPC RDF-to-Text System at WebNLG Challenge 2020
(Association for Computational Linguistics, 2020)
Conference report
Open AccessThis work describes the end-to-end system architecture presented at WebNLG Challenge 2020. The system follows the traditional Machine Translation (MT) pipeline, based on the Transformer model, applied in most text-to-text ... -
The TALP-UPC participation in WMT21 news translation task: an mBART-based NMT approach
(Association for Computational Linguistics, 2021)
Conference report
Open AccessThis paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission ... -
Enriching the transformer with linguistic factors for low-resource machine translation
(Incoma, Ltd., 2021)
Conference report
Open AccessIntroducing 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 ... -
Self-supervised deep learning approaches to speaker recognition: A Ph.D. Thesis overview
(International Speech Communication Association (ISCA), 2021)
Conference lecture
Open AccessRecent advances in Deep Learning (DL) for speaker recognition have improved the performance but are constrained to the need of labels for the background data, which is difficult in prac- tice. In i-vector based speaker ... -
End-to-end speech translation with pre-trained models and adapters: UPC at IWSLT 2021
(Association for Computational Linguistics, 2021)
Conference report
Open AccessThis paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group. The task consists of building a system capable of translating English audio recordings extracted ... -
Soporte universitario al paso a docencia virtual debido a la COVID-19 y su seguimiento por parte del profesorado
(Asociación Española de Ingeniería de Proyectos (AEIPRO), 2021)
Conference report
Open AccessLa virtualidad de las clases universitarias es una realidad imperativa desde el primer confinamiento provocado por la COVID-19. Cada universidad ha tenido un proceso de adaptación diferente y en grandes universidades con ...
RSS 1.0