Cristina España-Bonet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Cristina España-Bonet has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Josef van Genabith
German Research Center for Artificial Intelligence (DFKI GmbH) Saarland Informatics Campus Saarbrücken Germany
6 shared publications - Alberto Barrón-Cedeño
DIT, Università di Bologna, Forlì, Italy
5 shared publications - Yasser Hamidullah
German Research Center for Artificial Intelligence (DFKI GmbH) Saarland Informatics Campus Saarbrücken Germany
5 shared publications Josef van Genabith
Saarland Informatics Campus Saarland University Germany
4 shared publications- David Ifeoluwa Adelani
Spoken Language Systems (LSV) Saarland University Saarland Informatics Campus Germany
2 shared publications Josef Van Genabith
Saarland University
2 shared publications
Latest Publications
- Open Access
- 21 January 2026
- Published by Elsevier in Computer Speech & Language
- Vol. 100
LaFresCat: A studio-quality Catalan multi-accent speech dataset for text-to-speech synthesis
- 21 January 2026
- Published by Elsevier in Computer Speech & Language
- Vol. 100
Open AccessLaFresCat: A studio-quality Catalan multi-accent speech dataset for text-to-speech synthesis
- Open Access
Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media
Most existing sign language translation (SLT) datasets are limited in scale, lack multilingual coverage, and are costly to curate due to their reliance on expert annotation and controlled recording setup. Recently, Vision Language Models (VLMs) have demonstrated strong capabilities as evaluators and real-time assistants. Despite these advancements, their potential remains untapped in the context of sign language dataset acquisition. To bridge this gap, we introduce the first automated annotation and filtering framework that utilizes VLMs to reduce reliance on manual effort while preserving data quality. Our method is applied to TikTok videos across eight sign languages and to the already curated YouTube-SL-25 dataset in German Sign Language for the purpose of additional evaluation. Our VLM-based pipeline includes a face visibility detection, a sign activity recognition, a text extraction from video content, and a judgment step to validate alignment between video and text, implementing generic filtering, annotation and validation steps. Using the resulting corpus, TikTok-SL-8, we assess the performance of two off-the-shelf SLT models on our filtered dataset for German and American Sign Languages, with the goal of establishing baselines and evaluating the robustness of recent models on automatically extracted, slightly noisy data. Our work enables scalable, weakly supervised pretraining for SLT and facilitates data acquisition from social media.
Open AccessSeeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media
Most existing sign language translation (SLT) datasets are limited in scale, lack multilingual coverage, and are costly to curate due to their reliance on expert annotation and controlled recording setup. Recently, Vision Language Models (VLMs) have demonstrated strong capabilities as evaluators and real-time assistants. Despite these advancements, their potential remains untapped in the context of sign language dataset acquisition. To bridge this gap, we introduce the first automated annotation and filtering framework that utilizes VLMs to reduce reliance on manual effort while preserving data quality. Our method is applied to TikTok videos across eight sign languages and to the already curated YouTube-SL-25 dataset in German Sign Language for the purpose of additional evaluation. Our VLM-based pipeline includes a face visibility detection, a sign activity recognition, a text extraction from video content, and a judgment step to validate alignment between video and text, implementing generic filtering, annotation and validation steps. Using the resulting corpus, TikTok-SL-8, we assess the performance of two off-the-shelf SLT models on our filtered dataset for German and American Sign Languages, with the goal of establishing baselines and evaluating the robustness of recent models on automatically extracted, slightly noisy data. Our work enables scalable, weakly supervised pretraining for SLT and facilitates data acquisition from social media.
- Open Access
Spatio-temporal Sign Language Representation and Translation
This paper describes the DFKI-MLT submission to the WMT-SLT 2022 sign language translation (SLT) task from Swiss German Sign Language (video) into German (text). State-of-the-art techniques for SLT use a generic seq2seq architecture with customized input embeddings. Instead of word embeddings as used in textual machine translation, SLT systems use features extracted from video frames. Standard approaches often do not benefit from temporal features. In our participation, we present a system that learns spatio-temporal feature representations and translation in a single model, resulting in a real end-to-end architecture expected to better generalize to new data sets. Our best system achieved $5\pm1$ BLEU points on the development set, but the performance on the test dropped to $0.11\pm0.06$ BLEU points.Open AccessSpatio-temporal Sign Language Representation and Translation
This paper describes the DFKI-MLT submission to the WMT-SLT 2022 sign language translation (SLT) task from Swiss German Sign Language (video) into German (text). State-of-the-art techniques for SLT use a generic seq2seq architecture with customized input embeddings. Instead of word embeddings as used in textual machine translation, SLT systems use features extracted from video frames. Standard approaches often do not benefit from temporal features. In our participation, we present a system that learns spatio-temporal feature representations and translation in a single model, resulting in a real end-to-end architecture expected to better generalize to new data sets. Our best system achieved $5\pm1$ BLEU points on the development set, but the performance on the test dropped to $0.11\pm0.06$ BLEU points. - Open Access
SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based sentence embeddings, but up to now, these remain tied to a specific language and modality. In contrast, here we employ language-agnostic, multimodal embeddings trained on text and speech from multiple languages to supervise SLT, enabling direct multilingual translation. To address data scarcity, we propose a coupled augmentation method that combines multilingual target augmentations (i.e. translations into many languages) with video-level perturbations, improving model robustness. Experiments show consistent BLEURT gains over text-only sentence embedding supervision, with larger improvements in low-resource settings. Our results demonstrate that language-agnostic embedding supervision, combined with coupled augmentation, provides a scalable and semantically robust alternative to traditional SLT training.
Open AccessSONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based sentence embeddings, but up to now, these remain tied to a specific language and modality. In contrast, here we employ language-agnostic, multimodal embeddings trained on text and speech from multiple languages to supervise SLT, enabling direct multilingual translation. To address data scarcity, we propose a coupled augmentation method that combines multilingual target augmentations (i.e. translations into many languages) with video-level perturbations, improving model robustness. Experiments show consistent BLEURT gains over text-only sentence embedding supervision, with larger improvements in low-resource settings. Our results demonstrate that language-agnostic embedding supervision, combined with coupled augmentation, provides a scalable and semantically robust alternative to traditional SLT training.
- Open Access
Sign Language Translation with Sentence Embedding Supervision
State-of-the-art sign language translation (SLT) systems facilitate the learning process through gloss annotations, either in an end2end manner or by involving an intermediate step. Unfortunately, gloss labelled sign language data is usually not available at scale and, when available, gloss annotations widely differ from dataset to dataset. We present a novel approach using sentence embeddings of the target sentences at training time that take the role of glosses. The new kind of supervision does not need any manual annotation but it is learned on raw textual data. As our approach easily facilitates multilinguality, we evaluate it on datasets covering German (PHOENIX-2014T) and American (How2Sign) sign languages and experiment with mono- and multilingual sentence embeddings and translation systems. Our approach significantly outperforms other gloss-free approaches, setting the new state-of-the-art for data sets where glosses are not available and when no additional SLT datasets are used for pretraining, diminishing the gap between gloss-free and gloss-dependent systems.
Open AccessSign Language Translation with Sentence Embedding Supervision
State-of-the-art sign language translation (SLT) systems facilitate the learning process through gloss annotations, either in an end2end manner or by involving an intermediate step. Unfortunately, gloss labelled sign language data is usually not available at scale and, when available, gloss annotations widely differ from dataset to dataset. We present a novel approach using sentence embeddings of the target sentences at training time that take the role of glosses. The new kind of supervision does not need any manual annotation but it is learned on raw textual data. As our approach easily facilitates multilinguality, we evaluate it on datasets covering German (PHOENIX-2014T) and American (How2Sign) sign languages and experiment with mono- and multilingual sentence embeddings and translation systems. Our approach significantly outperforms other gloss-free approaches, setting the new state-of-the-art for data sets where glosses are not available and when no additional SLT datasets are used for pretraining, diminishing the gap between gloss-free and gloss-dependent systems.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 67-81
MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation
Uliana Sentsova, Debora Ciminari, Josef Van Genabith, Cristina España-Bonet. Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 67-81
Open AccessMultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation
Uliana Sentsova, Debora Ciminari, Josef Van Genabith, Cristina España-Bonet. Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10923-10938
Continual Learning in Multilingual Sign Language Translation
Shakib Yazdani, Josef Van Genabith, Cristina España-Bonet. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10923-10938
Open AccessContinual Learning in Multilingual Sign Language Translation
Shakib Yazdani, Josef Van Genabith, Cristina España-Bonet. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 425-434
Sign Language Translation with Sentence Embedding Supervision
Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 425-434
Open AccessSign Language Translation with Sentence Embedding Supervision
Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 3689-3711
Elote, Choclo and Mazorca: on the Varieties of Spanish
Cristina España-Bonet, Alberto Barrón-Cedeño. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 3689-3711
Open AccessElote, Choclo and Mazorca: on the Varieties of Spanish
Cristina España-Bonet, Alberto Barrón-Cedeño. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- Open Access
Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper
Neutrality is difficult to achieve and, in politics, subjective. Traditional media typically adopt an editorial line that can be used by their potential readers as an indicator of the media bias. Several platforms currently rate news outlets according to their political bias. The editorial line and the ratings help readers in gathering a balanced view of news. But in the advent of instruction-following language models, tasks such as writing a newspaper article can be delegated to computers. Without imposing a biased persona, where would an AI-based news outlet lie within the bias ratings? In this work, we use the ratings of authentic news outlets to create a multilingual corpus of news with coarse stance annotations (Left and Right) along with automatically extracted topic annotations. We show that classifiers trained on this data are able to identify the editorial line of most unseen newspapers in English, German, Spanish and Catalan. We then apply the classifiers to 101 newspaper-like articles written by ChatGPT and Bard in the 4 languages at different time periods. We observe that, similarly to traditional newspapers, ChatGPT editorial line evolves with time and, being a data-driven system, the stance of the generated articles differs among languages.
Open AccessMultilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper
Neutrality is difficult to achieve and, in politics, subjective. Traditional media typically adopt an editorial line that can be used by their potential readers as an indicator of the media bias. Several platforms currently rate news outlets according to their political bias. The editorial line and the ratings help readers in gathering a balanced view of news. But in the advent of instruction-following language models, tasks such as writing a newspaper article can be delegated to computers. Without imposing a biased persona, where would an AI-based news outlet lie within the bias ratings? In this work, we use the ratings of authentic news outlets to create a multilingual corpus of news with coarse stance annotations (Left and Right) along with automatically extracted topic annotations. We show that classifiers trained on this data are able to identify the editorial line of most unseen newspapers in English, German, Spanish and Catalan. We then apply the classifiers to 101 newspaper-like articles written by ChatGPT and Bard in the 4 languages at different time periods. We observe that, similarly to traditional newspapers, ChatGPT editorial line evolves with time and, being a data-driven system, the stance of the generated articles differs among languages.