Marta R. Costa-Jussà

research

∙ 09/20/2023

SpeechAlign: a Framework for Speech Translation Alignment Evaluation

Speech-to-Speech and Speech-to-Text translation are currently dynamic ar...

0 Belen Alastruey, et al. ∙

research

∙ 09/06/2023

Gender-specific Machine Translation with Large Language Models

Decoder-only Large Language Models (LLMs) have demonstrated potential in...

0 Eduardo Sanchez, et al. ∙

research

∙ 08/31/2023

The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages

Gender biases in language generation systems are challenging to mitigate...

0 Benjamin Müller, et al. ∙

research

∙ 08/22/2023

SeamlessM4T-Massively Multilingual Multimodal Machine Translation

What does it take to create the Babel Fish, a tool that can help individ...

0 Seamless Communication, et al. ∙

research

∙ 06/02/2023

Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23

This paper describes the submission of the UPC Machine Translation group...

0 Ioannis Tsiamas, et al. ∙

research

∙ 05/22/2023

Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale

We introduce a multilingual extension of the HOLISTICBIAS dataset, the l...

10 Marta R. Costa-Jussà, et al. ∙

research

∙ 05/21/2023

Explaining How Transformers Use Context to Build Predictions

Language Generation Models produce words based on the previous context. ...

0 Javier Ferrando, et al. ∙

research

∙ 05/19/2023

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

Our proposed method, ReSeTOX (REdo SEarch if TOXic), addresses the issue...

0 Javier García Gilabert, et al. ∙

research

∙ 05/19/2023

HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation

Hallucinations in machine translation are translations that contain info...

0 David Dale, et al. ∙

research

∙ 12/19/2022

SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations

Data scarcity is one of the main issues with the end-to-end approach for...

0 Ioannis Tsiamas, et al. ∙

research

∙ 12/16/2022

Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better

While the problem of hallucinations in neural machine translation has lo...

0 David Dale, et al. ∙

research

∙ 12/16/2022

BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric

End-to-End speech-to-speech translation (S2ST) is generally evaluated wi...

0 Mingda Chen, et al. ∙

research

∙ 10/28/2022

Efficient Speech Translation with Dynamic Latent Perceivers

Transformers have been the dominant architecture for Speech Translation ...

0 Ioannis Tsiamas, et al. ∙

research

∙ 10/06/2022

Toxicity in Multilingual Machine Translation at Scale

Machine Translation systems can produce different types of errors, some ...

1 Marta R. Costa-Jussà, et al. ∙

research

∙ 07/11/2022

No Language Left Behind: Scaling Human-Centered Machine Translation

Driven by the goal of eradicating language barriers on a global scale, m...

9 NLLB team, et al. ∙

research

∙ 05/23/2022

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

In Neural Machine Translation (NMT), each token prediction is conditione...

4 Javier Ferrando, et al. ∙

research

∙ 05/14/2022

Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation

Transformer-based models have been achieving state-of-the-art results in...

1 Gerard Sant, et al. ∙

research

∙ 04/19/2022

On the Locality of Attention in Direct Speech Translation

Transformers have achieved state-of-the-art results across multiple NLP ...

4 Belen Alastruey, et al. ∙

research

∙ 03/08/2022

Measuring the Mixing of Contextual Information in the Transformer

The Transformer architecture aggregates input information through the se...

7 Javier Ferrando, et al. ∙

research

∙ 02/12/2022

A multi-task semi-supervised framework for Text2Graph Graph2Text

The Artificial Intelligence industry regularly develops applications tha...

0 Oriol Domingo, et al. ∙

research

∙ 02/09/2022

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

Speech translation models are unable to directly process long audios, li...

2 Ioannis Tsiamas, et al. ∙

research

∙ 09/13/2021

Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

This work proposes an extensive analysis of the Transformer architecture...

0 Javier Ferrando, et al. ∙

research

∙ 07/07/2021

Efficient Transformer for Direct Speech Translation

The advent of Transformer-based models has surpassed the barriers of tex...

7 Belen Alastruey, et al. ∙

research

∙ 05/10/2021

UPC's Speech Translation System for IWSLT 2021

This paper describes the submission to the IWSLT 2021 offline speech tra...

1 Gerard I. Gállego, et al. ∙

research

∙ 05/03/2021

Impact of Gender Debiased Word Embeddings in Language Modeling

Gender, race and social biases have recently been detected as evident ex...

0 Christine Basta, et al. ∙

research

∙ 04/07/2021

How to Write a Bias Statement: Recommendations for Submissions to the Workshop on Gender Bias in NLP

At the Workshop on Gender Bias in NLP (GeBNLP), we'd like to encourage a...

0 Christian Hardmeier, et al. ∙

research

∙ 02/17/2021

Sparsely Factored Neural Machine Translation

The standard approach to incorporate linguistic information to neural ma...

0 Noe Casas, et al. ∙

research

∙ 12/24/2020

Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters

Multilingual Neural Machine Translation architectures mainly differ in t...

21 Marta R. Costa-Jussà, et al. ∙

research

∙ 12/17/2020

Continual Lifelong Learning in Natural Language Processing: A Survey

Continual learning (CL) aims to enable information systems to learn from...

0 Magdalena Biesialska, et al. ∙

research

∙ 11/02/2020

Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders

Current end-to-end approaches to Spoken Language Translation (SLT) rely ...

6 Carlos Escolano, et al. ∙

research

∙ 10/27/2020

Evaluating Gender Bias in Speech Translation

The scientific community is more and more aware of the necessity to embr...

7 Marta R. Costa-Jussà, et al. ∙

research

∙ 05/29/2020

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

We propose a modular architecture of language-specific encoder-decoders ...

0 Carlos Escolano, et al. ∙

research

∙ 05/27/2020

MT-Adapted Datasheets for Datasets: Template and Repository

In this report we are taking the standardized model proposed by Gebru et...

0 Marta R. Costa-Jussà, et al. ∙

research

∙ 05/20/2020

Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources

In this work, we present an effective method for semantic specialization...

0 Magdalena Biesialska, et al. ∙

research

∙ 04/17/2020

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

Introducing factors, that is to say, word features such as linguistic in...

0 Jordi Armengol-Estapé, et al. ∙

research

∙ 04/14/2020

Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders

State-of-the-art multilingual machine translation relies on a universal ...

0 Carlos Escolano, et al. ∙

research

∙ 04/05/2020

Syntax-driven Iterative Expansion Language Models for Controllable Text Generation

The dominant language modeling paradigms handle text as a sequence of di...

0 Noe Casas, et al. ∙

research

∙ 02/21/2020

Refinement of Unsupervised Cross-Lingual Word Embeddings

Cross-lingual word embeddings aim to bridge the gap between high-resourc...

0 Magdalena Biesialska, et al. ∙

research

∙ 12/10/2019

GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies

We introduce GeBioToolkit, a tool for extracting multilingual parallel c...

0 Marta R. Costa-Jussà, et al. ∙

research

∙ 08/03/2019

The TALP-UPC System for the WMT Similar Language Task: Statistical vs Neural Machine Translation

Although the problem of similar language translation has been an area of...

0 Magdalena Biesialska, et al. ∙

research

∙ 07/01/2019

Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations

The main alternatives nowadays to deal with sequences are Recurrent Neur...

0 Carlos Escolano, et al. ∙

research

∙ 06/28/2019

From Bilingual to Multilingual Neural Machine Translation by Incremental Training

Multilingual Neural Machine Translation approaches are based on the use ...

0 Carlos Escolano, et al. ∙

research

∙ 05/16/2019

Joint Source-Target Self Attention with Locality Constraints

The dominant neural machine translation models are based on the encoder-...

0 José A. R. Fonollosa, et al. ∙

research

∙ 05/15/2019

Towards Interlingua Neural Machine Translation

A common intermediate language representation or an interlingua is the h...

0 Carlos Escolano, et al. ∙

research

∙ 04/18/2019

Evaluating the Underlying Gender Bias in Contextualized Word Embeddings

Gender bias is highly impacting natural language processing applications...

0 Christine Basta, et al. ∙

research

∙ 01/10/2019

Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques

Neural machine translation has significantly pushed forward the quality ...

0 Joel Escudé Font, et al. ∙

research

∙ 10/15/2018

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

Universal language representation is the holy grail in machine translati...

0 Carlos Escolano, et al. ∙

research

∙ 07/02/2018

A Neural Approach to Language Variety Translation

In this paper we present the first neural-based machine translation syst...

0 Marta R. Costa-Jussà, et al. ∙

research

∙ 03/19/2018

English-Catalan Neural Machine Translation in the Biomedical Domain through the cascade approach

This paper describes the methodology followed to build a neural machine ...

0 Marta R. Costa-Jussà, et al. ∙

research

∙ 07/24/2017

Character-level Intra Attention Network for Natural Language Inference

Natural language inference (NLI) is a central problem in language unders...

0 Han Yang, et al. ∙

Marta R. Costa-Jussà

Featured Co-authors