| 2025 | ACL | LCFO: Long Context and Long Form Output Dataset and Benchmarking. | Marta R. Costa-juss, Pierre Andrews, Mariano Coria Meglioli, Joy Chen, Joe Chuang, David Dale, Christophe Ropers, Alexandre Mourachko, Eduardo Snchez, Holger Schwenk, Tuan Tran, Arina Turkatenko, Carleigh Wood |
| 2025 | ACL | 2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset Download PDF. | Marta R. Costa-juss, Bokai Yu, Pierre Andrews, Belen Alastruey, Necati Cihan Camgz, Joe Chuang, Jean Maillard, Christophe Ropers, Arina Turkatenko, Carleigh Wood |
| 2025 | ACL | Improving Language and Modality Transfer in Translation by Character-level Modeling. | Ioannis Tsiamas, David Dale, Marta R. Costa-juss |
| 2025 | EMNLP | BOUQuET : dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation. | Pierre Andrews, Mikel Artetxe, Mariano Coria Meglioli, Marta R. Costa-juss, Joe Chuang, David Dale, Mark Duppenthaler, Nathanial Paul Ekberg, Cynthia Gao, Daniel Edward Licht, Jean Maillard, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Eduardo Snchez, Ioannis Tsiamas, Arina Turkatenko, Albert Ventayol-Boada, Shireen Yates |
| 2025 | NAACL | On the Role of Speech Data in Reducing Toxicity Detection Bias. | Samuel J. Bell, Mariano Coria Meglioli, Megan Richards, Eduardo Snchez, Christophe Ropers, Skyler Wang, Adina Williams, Levent Sagun, Marta R. Costa-juss |
| 2024 | ACL | MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector. | Marta R. Costa-juss, Mariano Coria Meglioli, Pierre Andrews, David Dale, Prangthip Hansanti, Elahe Kalbassi, Alexandre Mourachko, Christophe Ropers, Carleigh Wood |
| 2024 | ACL | Pushing the Limits of Zero-shot End-to-End Speech Translation. | Ioannis Tsiamas, Gerard I. Gllego, Jos A. R. Fonollosa, Marta R. Costa-juss |
| 2024 | COLING | SpeechAlign: A Framework for Speech Translation Alignment Evaluation. | Belen Alastruey, Aleix Sant, Gerard I. Gllego, David Dale, Marta R. Costa-juss |
| 2024 | EAMT | Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation. | Marta R. Costa-juss, David Dale, Maha Elbayad, Bokai Yu |
| 2024 | EAMT | ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation. | Javier Garca Gilabert, Carlos Escolano, Marta R. Costa-juss |
| 2024 | EMNLP | Unveiling the Role of Pretraining in Direct Speech Translation. | Belen Alastruey, Gerard I. Gllego, Marta R. Costa-juss |
| 2024 | EMNLP | BLASER 2.0: a metric for evaluation and quality estimation of massively multilingual speech and text translation. | David Dale, Marta R. Costa-juss |
| 2024 | EMNLP | On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task. | Javier Ferrando, Marta R. Costa-juss |
| 2023 | ACL | BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric. | Mingda Chen, Paul-Ambroise Duquenne, Pierre Andrews, Justine Kao, Alexandre Mourachko, Holger Schwenk, Marta R. Costa-juss |
| 2023 | ACL | Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better. | David Dale, Elena Voita, Loc Barrault, Marta R. Costa-juss |
| 2023 | ACL | Explaining How Transformers Use Context to Build Predictions. | Javier Ferrando, Gerard I. Gllego, Ioannis Tsiamas, Marta R. Costa-juss |
| 2023 | EMNLP | Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale. | Marta R. Costa-juss, Pierre Andrews, Eric Michael Smith, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Daniel Licht, Carleigh Wood |
| 2023 | EMNLP | Toxicity in Multilingual Machine Translation at Scale. | Marta R. Costa-juss, Eric Michael Smith, Christophe Ropers, Daniel Licht, Jean Maillard, Javier Ferrando, Carlos Escolano |
| 2023 | EMNLP | HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation. | David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Loc Barrault, Marta R. Costa-juss |
| 2023 | EMNLP | SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations. | Ioannis Tsiamas, Jos A. R. Fonollosa, Marta R. Costa-juss |
| 2023 | ICASSP | Efficient Speech Translation with Dynamic Latent Perceivers. | Ioannis Tsiamas, Gerard I. Gllego, Jos A. R. Fonollosa, Marta R. Costa-juss |
| 2022 | AAAI | Interpreting Gender Bias in Neural Machine Translation: Multilingual Architecture Matters. | Marta R. Costa-juss, Carlos Escolano, Christine Basta, Javier Ferrando, Roser Batlle, Ksenia Kharitonova |
| 2022 | ACL | On the Locality of Attention in Direct Speech Translation. | Belen Alastruey, Javier Ferrando, Gerard I. Gllego, Marta R. Costa-juss |
| 2022 | EMNLP | Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer. | Javier Ferrando, Gerard I. Gllego, Belen Alastruey, Carlos Escolano, Marta R. Costa-juss |
| 2022 | EMNLP | Measuring the Mixing of Contextual Information in the Transformer. | Javier Ferrando, Gerard I. Gllego, Marta R. Costa-juss |
| 2022 | Interspeech | SHAS: Approaching optimal Segmentation for End-to-End Speech Translation. | Ioannis Tsiamas, Gerard I. Gllego, Jos A. R. Fonollosa, Marta R. Costa-juss |
| 2022 | LREC | Evaluating Gender Bias in Speech Translation. | Marta R. Costa-juss, Christine Basta, Gerard I. Gllego |
| 2021 | ASRU | Enabling Zero-Shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders. | Carlos Escolano, Marta R. Costa-juss, Jos A. R. Fonollosa, Carlos Segura |
| 2021 | EACL | Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders. | Carlos Escolano, Marta R. Costa-juss, Jos A. R. Fonollosa, Mikel Artetxe |
| 2021 | EMNLP | Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions. | Javier Ferrando, Marta R. Costa-juss |
| 2021 | RANLP | Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation. | Jordi Armengol-Estap, Marta R. Costa-juss, Carlos Escolano |
| 2020 | ACL | Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources. | Magdalena Biesialska, Bardia Rafieian, Marta R. Costa-juss |
| 2020 | ACL | Combining Subword Representations into Word-level Representations in the Transformer Architecture. | Noe Casas, Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2020 | COLING | Continual Lifelong Learning in Natural Language Processing: A Survey. | Magdalena Biesialska, Katarzyna Biesialska, Marta R. Costa-juss |
| 2020 | ECAI | Refinement of Unsupervised Cross-Lingual Word Embeddings. | Magdalena Biesialska, Marta R. Costa-juss |
| 2020 | LREC | Automatic Spanish Translation of SQuAD Dataset for Multi-lingual Question Answering. | Casimiro Pio Carrino, Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2020 | LREC | Abusive language in Spanish children and young teenager's conversations: data preparation and short text classification with contextual word embeddings. | Marta R. Costa-juss, Esther Gonzlez, Asuncin Moreno, Eudald Cumalat |
| 2020 | LREC | GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies. | Marta R. Costa-juss, Pau Li Lin, Cristina Espaa-Bonet |
| 2019 | ACL | From Bilingual to Multilingual Neural Machine Translation by Incremental Training. | Carlos Escolano, Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2019 | CICLING | Impact of Gender Debiased Word Embeddings in Language Modeling. | Christine Basta, Marta R. Costa-juss |
| 2019 | EMNLP | Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations. | Carlos Escolano, Marta R. Costa-juss, Elora Lacroux, Pere-Pau Vzquez |
| 2018 | ICLR | A differentiable BLEU loss. Analysis and first results. | Noe Casas, Jos A. R. Fonollosa, Marta R. Costa-juss |
| 2018 | IJCAI | From Feature to Paradigm: Deep Learning in Machine Translation (Extended Abstract). | Marta R. Costa-juss |
| 2017 | EMNLP | Byte-based Neural Machine Translation. | Marta R. Costa-juss, Carlos Escolano, Jos A. R. Fonollosa |
| 2017 | ESANN | Bridging deep and kernel methods. | Llus Belanche, Marta R. Costa-juss |
| 2016 | ACL | Character-based Neural Machine Translation. | Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2016 | CICLING | Combining Phrase and Neural-Based Machine Translation: What Worked and Did Not. | Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2016 | EAMT | Integration of machine translation paradigms. | Marta R. Costa-juss |
| 2014 | EACL | CHISPA on the GO: A mobile Chinese-Spanish translation service for travellers in trouble. | Jordi Centelles, Marta R. Costa-juss, Rafael E. Banchs |
| 2014 | Interspeech | A client mobile application for Chinese-Spanish statistical machine translation. | Jordi Centelles, Marta R. Costa-juss, Rafael E. Banchs |
| 2013 | IJCAI | Evaluating Indirect Strategies for Chinese - Spanish Statistical Machine Translation: Extended Abstract. | Marta R. Costa-juss, Carlos A. Henrquez Q., Rafael E. Banchs |
| 2013 | NAACL | Morphological, Syntactical and Semantic Knowledge in Statistical Machine Translation. | Marta R. Costa-juss, Chris Quirk |
| 2012 | COLING | Results from the ML4HMT-12 Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid Machine Translation. | Christian Federmann, Tsuyoshi Okita, Maite Melero, Marta R. Costa-juss, Toni Badia, Josef van Genabith |
| 2012 | LREC | BUCEADOR, a multi-language search engine for digital libraries. | Jordi Adell, Antonio Bonafonte, Antonio Cardenal Lpez, Marta R. Costa-juss, Jos A. R. Fonollosa, Asuncin Moreno, Eva Navas, Eduardo Rodrguez Banga |
| 2012 | LREC | A Richly Annotated, Multilingual Parallel Corpus for Hybrid Machine Translation. | Eleftherios Avramidis, Marta R. Costa-juss, Christian Federmann, Josef van Genabith, Maite Melero, Pavel Pecina |
| 2012 | LREC | The ML4HMT Workshop on Optimising the Division of Labour in Hybrid Machine Translation. | Christian Federmann, Eleftherios Avramidis, Marta R. Costa-juss, Josef van Genabith, Maite Melero, Pavel Pecina |
| 2012 | LREC | Holaaa!! writin like u talk is kewl but kinda hard 4 NLP. | Maite Melero, Marta R. Costa-juss, Judith Domingo, Montse Marquina, Mart Quixal |
| 2011 | IJCNLP | Enhancing scarce-resource language translation through pivot combinations. | Marta R. Costa-juss, Carlos A. Henrquez Q., Rafael E. Banchs |
| 2010 | EAMT | Integration of statistical collocation segmentations in a phrase-based statistical machine translation system. | Marta R. Costa-juss, Vidas Daudaravicius, Rafael E. Banchs |
| 2010 | EAMT | Linguistic-based Evaluation Criteria to identify Statistical Machine Translation Errors. | Mireia Farrs, Marta R. Costa-juss, Jos B. Mario, Jos A. R. Fonollosa |
| 2010 | ICAART | Where are you From? - Tell Me HOW you Write and I Will Tell you WHO you are. | Marta R. Costa-juss, Rafael E. Banchs, Joan Codina |
| 2010 | LREC | Using Linear Interpolation and Weighted Reordering Hypotheses in the Moses System. | Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2010 | LREC | Automatic and Human Evaluation Study of a Rule-based and a Statistical Catalan-Spanish Machine Translation Systems. | Marta R. Costa-juss, Mireia Farrs, Jos B. Mario, Jos A. R. Fonollosa |
| 2010 | NAACL | Opinion Mining of Spanish Customer Comments with Non-Expert Annotations on Mechanical Turk. | Bart Mellebeek, Francesc Benavent, Jens Grivolla, Joan Codina, Marta R. Costa-juss, Rafael E. Banchs |
| 2009 | EAMT | Improving a Catalan-Spanish Statistical Translation System using Morphosyntactic Knowledge. | Mireia Farrs, Marta R. Costa-juss, Marc Poch, Adolfo Hernndez, Jos B. Mario |
| 2008 | AMTA | Computing multiple weighted reordering hypotheses for a phrase-based statistical machine translation system. | Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2008 | LREC | Using Reordering in Statistical Machine Translation based on Alignment Block Classification. | Marta R. Costa-juss, Jos A. R. Fonollosa, Enric Monte |
| 2007 | EMNLP | Smooth Bilingual N-Gram Translation. | Holger Schwenk, Marta R. Costa-juss, Jos A. R. Fonollosa |
| 2007 | NAACL | Analysis and System Combination of Phrase- and N-Gram-Based Statistical Machine Translation Systems. | Marta R. Costa-juss, Josep Maria Crego, David Vilar, Jos A. R. Fonollosa, Jos B. Mario, Hermann Ney |
| 2006 | EMNLP | Statistical Machine Reordering. | Marta R. Costa-juss, Jos A. R. Fonollosa |