Search Results for author: Carlos Escolano

Found 25 papers, 6 papers with code

Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022

1 code implementation IWSLT (ACL) 2022 Ioannis Tsiamas, Gerard I. Gállego, Carlos Escolano, José Fonollosa, Marta R. Costa-jussà

We further investigate the suitability of different speech encoders (wav2vec 2. 0, HuBERT) for our models and the impact of knowledge distillation from the Machine Translation model that we use for the decoder (mBART).

Knowledge Distillation Machine Translation +2

Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation

1 code implementation29 Sep 2023 Casimiro Pio Carrino, Carlos Escolano, José A. R. Fonollosa

Our approach seeks to enhance cross-lingual QA transfer using a high-performing multilingual model trained on a large-scale dataset, complemented by a few thousand aligned QA examples across languages.

Cross-Lingual Question Answering Cross-Lingual Transfer +3

ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation

1 code implementation19 May 2023 Javier García Gilabert, Carlos Escolano, Marta R. Costa-jussà

Our proposed method, ReSeTOX (REdo SEarch if TOXic), addresses the issue of Neural Machine Translation (NMT) generating translation outputs that contain toxic words not present in the input.

Machine Translation NMT +1

Toxicity in Multilingual Machine Translation at Scale

no code implementations6 Oct 2022 Marta R. Costa-jussà, Eric Smith, Christophe Ropers, Daniel Licht, Jean Maillard, Javier Ferrando, Carlos Escolano

We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages.

Hallucination Machine Translation +1

Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

1 code implementation23 May 2022 Javier Ferrando, Gerard I. Gállego, Belen Alastruey, Carlos Escolano, Marta R. Costa-jussà

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step).

Machine Translation NMT +2

A multi-task semi-supervised framework for Text2Graph & Graph2Text

1 code implementation12 Feb 2022 Oriol Domingo, Marta R. Costa-jussà, Carlos Escolano

The proposed solution, a T5 architecture, is trained in a multi-task semi-supervised environment, with our collected non-parallel data, following a cycle training regime.

Information Retrieval Retrieval +1

End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021

1 code implementation ACL (IWSLT) 2021 Gerard I. Gállego, Ioannis Tsiamas, Carlos Escolano, José A. R. Fonollosa, Marta R. Costa-jussà

Our submission also uses a custom segmentation algorithm that employs pre-trained Wav2Vec 2. 0 for identifying periods of untranscribable text and can bring improvements of 2. 5 to 3 BLEU score on the IWSLT 2019 test set, as compared to the result with the given segmentation.

Ranked #2 on Speech-to-Text Translation on MuST-C EN->DE (using extra training data)

Segmentation Speech-to-Text Translation +1

Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders

no code implementations29 May 2020 Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa, Mikel Artetxe

We propose a modular architecture of language-specific encoder-decoders that constitutes a multilingual machine translation system that can be incrementally extended to new languages without the need for retraining the existing system when adding new languages.

Machine Translation Natural Language Inference +2

Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation

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.

Machine Translation Translation

From Bilingual to Multilingual Neural Machine Translation by Incremental Training

no code implementations ACL 2019 Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system.

Machine Translation Translation

Towards Interlingua Neural Machine Translation

no code implementations15 May 2019 Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa

By adding and forcing this interlingual loss, we are able to train multiple encoders and decoders for each language, sharing a common intermediate representation.

Machine Translation Translation

(Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation

no code implementations15 Oct 2018 Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa

Preliminary results on the WMT 2017 Turkish/English task shows that the proposed architecture is capable of learning a universal language representation and simultaneously training both translation directions with state-of-the-art results.

Machine Translation Sentence +1

The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task

no code implementations WS 2018 Noe Casas, Carlos Escolano, Marta R. Costa-juss{\`a}, Jos{\'e} A. R. Fonollosa

In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English and Estonian-English within the multi-lingual subtrack.

Machine Translation Translation

Morphology Generation for Statistical Machine Translation using Deep Learning Techniques

no code implementations7 Oct 2016 Marta R. Costa-jussà, Carlos Escolano

In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem.

Classification Gender Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.