About me
I am a researcher at Inria, Paris in the ALMAnaCH team, working on Natural Language Processing (NLP) and more specifically Machine Translation (MT). I was previously a research associate at the University of Edinburgh, working on MT for low-resource languages, having completed my PhD on the contextual MT of dialogue at the LIMSI laboratory (now the LISN) in 2018 under the supervision of Sophie Rosset and Thomas Lavergne.
Research Experience
Please see my CV for a complete list of my research and teaching experience.
Natural Language Processing
and Machine Translation.
Holder of a "springboard" chair position in the PRAIRIE research institute (2021-present)
Holder of a "springboard" chair position in the PRAIRIE research institute (2021-present)
Supervised by Alexandra
Birch. Working on the MTStretch
fellowship (held by Alexandra Birch) and the
GoURMET EU
project (leader of the work package on morphological modelling)
Going beyond the sentence: Machine Translation of Dialogue in Context
Supervised by Sophie Rosset and Thomas Lavergne
Supervised by Sophie Rosset and Thomas Lavergne
Working with Alexandra Birch, Rico Sennrich and
Barry Haddow
Boosting for model selection in syntactic parsing
Supervised by Benoit Crabbé
Supervised by Benoit Crabbé
Modelling communicative acts for an embodied conversational agent
Supervised by Frédéric Landragin and Chloé Clavel
Supervised by Frédéric Landragin and Chloé Clavel
Tesnière Lucien (2015), Elements of structural syntax, translated by Timothy Osborne and Sylvain Kahane, John Benjamins, Amsterdam, U. Paris X.
Annotation, development and
semi-automatic correction of a treebank of spoken French for
syntactic dependencies (Rhapsodie Treebank of
Spoken French).
Supervised by Sylvain Kahane
Supervised by Sylvain Kahane
Publications
Phd Thesis
Going beyond the sentence: Contextual Machine Translation of Dialogue
Rachel Bawden supervised by Sophie Rosset and Thomas Lavergne.
29th November 2018. LIMSI, CNRS, Université Paris-Sud, Université Paris-Saclay.
Committee members:
Rachel Bawden supervised by Sophie Rosset and Thomas Lavergne.
29th November 2018. LIMSI, CNRS, Université Paris-Sud, Université Paris-Saclay.
Committee members:
- President: Nicolas Sabouret
- Reviewers: Jörg Tiedemann and Loïc Barrault
- Examiners: Lucia Specia and Andrei Popescu-Belis
Journal articles
Ancien ou moderne? Pistes computationnelles pour l’analyse graphématique des textes écrits au XVIIe siècle
Simon Gabay, Philippe Gambette, Rachel Bawden, Benoît Sagot (2022).
In Linx. Revue des linguistes de l’université Paris X Nanterre. Département de Sciences du langage 85, Université Paris Ouest.
Survey of low-resource machine translation
Barry Haddow, Rachel Bawden, Antonio Valerio Miceli
Barone, Jindřich Helcl, Alexandra Birch (2022)
Computational Linguistics. 48(3):673-732..
Le changement linguistique au XVIIe s.: nouvelles approches scriptométriques.
Simon Gabay, Rachel Bawden, Philippe Gambette, Jonathan Poinhos, Eleni Kogkitsidou, Benoît Sagot (2022).
SHS Web of Conferences 138, 02006.
DiaBLa: A Corpus of Bilingual Spontaneous Written
Dialogues for Machine Translation.
Rachel Bawden, Sophie Rosset, Thomas Lavergne, Eric Bilinski (2020).
Language Resources and Evaluation. DOI: 10.1007/s10579-020-09514-4
Dataset,
interface
and website
Towards the generation of dialogue acts in socio-effective ECAs.
Rachel Bawden, Chloé Clavel and Frédéric Landragin (2016). Language Resources and Evaluation. 4(2):821-838. Springer Netherlands. First online 31 July 2015. doi:10.1007/s10579-015-9312-9
Rachel Bawden, Chloé Clavel and Frédéric Landragin (2016). Language Resources and Evaluation. 4(2):821-838. Springer Netherlands. First online 31 July 2015. doi:10.1007/s10579-015-9312-9
Conference papers
Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation.
Matthieu Futeral, Cordelia Schmid, Ivan Laptev, Benoît
Sagot and Rachel Bawden (2023).
In Proceedings of the Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM.
Rachel Bawden and François Yvon (2023).
in Proceedings of the 24th Annual
Conference of the European Association for Machine
Translation. EAMT'23. Pages 157–170. Tampere, Finland.
Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages.
Sonal Sannigrahi and Rachel Bawden (2023).
In Proceedings of the 24th Annual
Conference of the European Association for Machine
Translation. EAMT'23. Pages 181–192. Tampere, Finland.
MaTOS: traduction automatique pour la science ouverte.
Maud Bénard, Alexandra Mestivier, Natalie Kubler, Lichao
Zhu, Rachel Bawden, Eric De La Clergerie, Laurent Romary,
Mathilde Huguin, Jean-François Nominé, Ziqian Peng and François Yvon (2022).
In Actes de la 30e Conférence sur le
Traitement Automatique des Langues
Naturelles. TALN'23. Paris, France.
Cross-lingual Strategies for Low-resource Language Modeling: A Study on Five Indic Dialects.
Niyati Bafna, Cristina España-Bonet, Josef van Genabith,
Benoît Sagot and Rachel Bawden (2023).
In Actes de la 30e Conférence sur le Traitement Automatique des Langues Naturelles.
TALN'23. Paris, France.
Gallic(orpor)a: Extraction, annotation et diffusion de l’information textuelle et visuelle en diachronie longue.
Benoît Sagot, Laurent Romary, Rachel Bawden, Pedro Javier Ortiz Suárez, Kelly Christensen, Simon Gabay, Ariane Pinche, Jean-Baptiste Camps (2022).
In Actes de DataLab de la BnF: Restitution des travaux 2022.
Findings of the WMT 2022 Biomedical Translation Shared Task: Monolingual Clinical Case Reports.
Mariana Neves, Antonio Jimeno Yepes, Amy Siu, Roland Roller, Philippe Thomas, Maika Vicente Navarro, Lana Yeganova, Dina Wiemann, Giorgio Maria Di Nunzio, Federica Vezzani, Christel Gérardin, Rachel Bawden, Darryl Johan Estrada, Salvador Lima-López, Eulàlia Farré-Maduell, Martin Krallinger, Cristian Grozea, Aurélie Névéol (2022).
In Proceedings of the Seventh Conference
on Machine Translation. WMT'22. Pages 694-723. Abu
Dhabi, United Arab Emirates.
Inria-ALMAnaCH at WMT 2022: Does Transcription Help Cross-Script Machine Translation?
Jesujoba Alabi, Lydia Nishimwe, Benjamin Muller, Camille
Rey, Benoît Sagot, Rachel Bawden (2022).
In Proceedings of the Seventh Conference
on Machine Translation. WMT'22. Pages 233-243. Abu
Dhabi, United Arab Emirates.
Findings of the 2022 conference on machine translation (WMT22).
Tom Kocmi, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich,
Christian Federmann, Mark Fishel, Thamme Gowda, Yvette
Graham, Roman Grundkiewicz, Barry Haddow, Rebecca
Knowles, Philipp Koehn, Christof Monz, Makoto Morishita,
Masaaki Nagata, Toshiaki Nakazawa, Michal Novák, Martin
Popel, Maja Popović (2022).
In Proceedings of the Seventh Conference
on Machine Translation. WMT'22. Pages 1-45. Abu
Dhabi, United Arab Emirates.
Vers l’étude linguistique sur données artificielles.
Simon Gabay, Rachel Bawden,
Benoît Sagot, Philippe Gambette. (2022)
In Proceedings of Variation (s) en français. Nancy, France.
Complex Labelling and Similarity Prediction in Legal Texts: Automatic Analysis of France’s Court of Cassation Rulings.
Thibault Charmet, Inès Cherichi, Matthieu Allain, Urszula
Czerwinska, Amaury Fouret, Benoît Sagot and Rachel Bawden (2022).
In Proceedings of the 13th Language
Resources and Evaluation
Conference. LREC'22. Pages 4754–4766. Marseille, France.
From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French.
Simon Gabay, Pedro Ortiz Suarez, Alexandre Bartz, Alix
Chagué, Rachel Bawden, Philippe Gambette, Benoît Sagot (2022).
In Proceedings of the 13th Language
Resources and Evaluation
Conference. LREC'22. Pages 3367–3374. Marseille, France.
Automatic Normalisation of Early Modern French.
Rachel Bawden, Jonathan Poinhos, Eleni Kogkitsidou, Philippe Gambette, Benoît Sagot and Simon Gabay (2022).
In Proceedings of the 13th Language
Resources and Evaluation
Conference. LREC'22. Pages 3354–3366. Marseille, France.
Le projet FREEM: ressources, outils et enjeux pour l’étude du français d’Ancien Régime (The FREEM project: Resources, tools and challenges for the study of Ancien Régime French).
Simon Gabay, Pedro Ortiz Suarez, Rachel Bawden, Alexandre Bartz, Philippe Gambette, Benoît Sagot (2022).
In Actes de la 29e Conférence sur le
Traitement Automatique des Langues Naturelles. Volume 1:
conférence principale. TALN'22. Pages 154-165. Avignon, France.
Multitask Prompt Tuning Enables Zero-Shot Task Generalization.
Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach,
Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud
Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful
Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma,
Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal
Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian
Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin
Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Fevry, Jason Alan Fries, Ryan Teehan, Tali Bers, Stella Biderman, Leo Gao, Thomas Wolf, Alexander M. Rush (2022).
In Proceedings of the 10th International
Conference on Learning Representations. ICLR'22. Online.
Findings of the WMT 2021 biomedical translation shared task: Summaries of animal experiments as new test set.
Lana Yeganova, Dina Wiemann, Mariana Neves, Federica Vezzani, Amy Siu, Iñigo Jauregi
Unanue, Maite Oronoz, Nancy Mah, Aurélie Névéol, David Martinez, Rachel Bawden, Giorgio Maria Di Nunzio, Roland Roller, Philippe Thomas, Cristian Grozea, Olatz Perez de Viñaspre, Maika Vicente Navarro and Antonio Jimeno Yepes (2021).
In Proceedings of the 6th Conference on
Machine Translation. WMT'2021. Online.
Expanding the content model of annotation Block.
Alexandre Bartz, Juliette Janes, Laurent Romary, Philippe
Gambette, Rachel Bawden, Pedro
Javier Ortiz Suárez, Benoît Sagot, Simon Gabay (2021).
In Proceedings of Next Gen TEI, 2021-TEI Conference and Members’ Meeting.
Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task?
Clémentine Fourrier, Rachel Bawden
and Benoît Sagot (2021).
In ACL-IJCNLP 2021-Findings of the Association for Computational Linguistics. ACL-Findings'2021.
Pages 846-861. Online.
Few-shot learning through contextual data augmentation.
Farid Arthaud, Rachel Bawden and Alexandra Birch (2021).
In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. EACL'2021. Online.
A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing.
Rachel Bawden, Biao Zhang, Lisa Yankovskaya, Andre Tättar and Matt Post (2020).
In Proceedings of the 2020 Conference on
Empirical Methods in Natural Language Processing:
Findings. EMNLP'20. Pages 918–932. Online.
The University of Edinburgh-Uppsala University's Submission to the WMT 2020 Chat Translation Task.
Nikita Moghe, Christian Hardmeier and Rachel Bawden (2020).
In Proceedings of the 5th Conference on
Machine Translation. WMT'20. Pages 473–478. Online.
ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT'20 Metrics Shared Task.
Rachel Bawden, Biao Zhang, Andre Tättar and Matt Post (2020).
In Proceedings of the 5th Conference on
Machine Translation. WMT'20. Pages 887–894. Online.
The University of Edinburgh's English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task.
Rachel Bawden, Alexandra Birch, Radina Dobreva, Arturo Oncevay, Antonio Valerio Miceli Barone and Philip Williams (2020).
In Proceedings of the 5th Conference on
Machine Translation. WMT'20. Pages 92–99. Online.
Findings of the WMT 2020 Biomedical Translation Shared Task: Basque, Italian and Russian as New Additional Languages.
Rachel Bawden, Giorgio Maria Di Nunzio, Cristian Grozea, Iñigo Jauregi Unanue, Antonio Jimeno Yepes, Nancy Mah, David Martinez, Aurélie Névéol, Mariana Neves, Maite Oronoz, Olatz Perez de Viñaspre, Massimo Piccardi, Roland Roller, Amy Siu, Philippe Thomas, Federica Vezzani, Maika Vicente Navarro, Dina Wiemann, Lana Yeganova (2020).
In Proceedings of the 5th Conference on
Machine Translation. WMT'20. Pages 660–687. Online.
Document-level Neural MT: A Systematic Comparison.
António Lopes, M. Amin Farajian, Rachel Bawden, Michael Zhang and André T. Martins (2020).
In Proceedings of the 22nd
Annual Conference of the European Association for
Machine Translation. EAMT'20. Pages 225–234. Lisbon, Portugal.
Dataset
Architecture of a Scalable, Secure and Resilient Translation Platform for Multilingual News Media.
Susie Coleman, Andrew Secker, Rachel Bawden, Barry Haddow and Alexandra Birch (2020).
In Proceedings of the 1st International
Workshop on Language Technology Platforms. IWLPT'20. Marseille, France.
Document Sub-structure in Neural Machine Translation.
Radina Dobreva, Jie Zhou, and Rachel Bawden (2020).
In Proceedings of the 12th Language Resources and Evaluation Conference. LREC'20. Marseille, France.
Datasets
The University of Edinburgh’s Submissions to the WMT19 News Translation Task (Updated version).
Rachel Bawden, Nikolay Bogoychev, Ulrich Germann, Roman Grundkiewicz, Faheem Kirefu, Antonio Valerio Miceli Barone, and Alexandra Birch (2019).
In Proceedings of the Fourth Conference
on Machine Translation. WMT'19. Florence, Italy.
Gujarati models
Findings of the WMT 2019 Biomedical Translation Shared Task: Evaluation for MEDLINE Abstracts and Biomedical Terminologies.
Rachel Bawden, Kevin Bretonnel Cohen, Cristian Grozea, Antonio Jimeno Yepes, Madeleine Kittner, Martin Krallinger, Nancy Mah, Aurelie Neveol, Mariana Neves, Felipe Soares, Amy Siu, Karin Verspoor, and Maika Vicente Navarro (2019).
In Proceedings of the Fourth Conference
on Machine Translation. WMT'19. Florence, Italy.
Global under-resourced media translation (GoURMET).
Alexandra Birch, Barry Haddow, Ivan Tito, Antonio Valerio Miceli Barone, Rachel Bawden, Felipe Sánchez-Martínez, Mikel L. Forcada, Miquel Esplà-Gomis, Víctor Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Wilker Aziz, Andrew Secker, and Peggy van der Kreeft (2019).
In Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks. Dublin, Ireland.
Evaluating Discourse Phenomena in Neural Machine Translation.
Rachel Bawden, Rico Sennrich, Alexandra
Birch and Barry Haddow (2018).
In Proceedings of the North American Chapter
of the Association for Computational Linguistics: Human
Language Technologies. NAACL'18. New Orleans, USA.
code and test set.
Detecting context-dependent sentences in parallel corpora.
Rachel Bawden, Thomas Lavergne and Sophie Rosset (2018).
In Proceedings of the 25th
Conférence sur le Traitement Automatique des
Langues Naturelles. TALN'18. Rennes, France.
Machine Translation, it's a question of style, innit? The case of English tag questions.
Rachel Bawden (2017).
In Proceedings of the 2017 Conference on
Empirical Methods in Natural Language Processing. EMNLP'17. Copenhagen, Denmark.
code
Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context.
Rachel Bawden (2017).
In Proceedings of the 19th REncontres
jeunes Chercheurs en Informatique pour le TAL. RECITAL 2017. Orléans, France.
Boosting for Efficient Model Selection for Syntactic Parsing.
Rachel Bawden and Benoit Crabbé (2016).
In Proceedings of the 26th International
Conference on Computational Linguistics. COLING'16. Osaka, Japan.
Investigating gender adaptation for speech translation.
Rachel Bawden, Guillaume Wisniewski and Heéleène Maynard (2016).
In Proceedings of the 23rd Conférence sur le Traitement Automatique des Langues Naturelles. TALN'16. Paris, France.
Correcting and Validating Syntactic Dependency in the Spoken French Treebank Rhapsodie.
Rachel Bawden, Marie-Amélie Bottala, Kim Gerdes and Sylvain Kahane (2014).
In Proceedings of the 9th International
Conference on Language Resources and Evaluation. LREC'14. Reykjavik, Iceland.
Preprints
Bloom: A 176b-parameter open-access multilingual language model.
Le Scao et al. (Many authors, including Rachel Bawden) (2022).
ArXiv.
Maskeval: Weighted MLM-based evaluation for text summarization and simplification.
Yu Lu Liu, Rachel Bawden, Thomas
Scialom, Benoît Sagot and Jackie Chi Kit Cheung (2022).
ArXiv.
Book chapters
Chapter 4. Microsyntactic annotation.
Sylvain Kahane, Kim Gerdes, and Rachel Bawden.
In Rhapsodie – A Prosodic and Syntactic Treebank for Spoken French.
Eds. Anne Lacheret-Dujour, Sylvain Kahane, and Paola Pietrandrea.
John Benjamins, Amsterdam, 2019.
Chapter 7. Annotation tools for syntax.
Kim Gerdes, Sylvain Kahane, Rachel Bawden, Julie Belião, Eric de la Clergerie, and Ilaine Wag.
In Rhapsodie – A Prosodic and Syntactic Treebank for Spoken French.
Eds. Anne Lacheret-Dujour, Sylvain Kahane, and Paola Pietrandrea.
John Benjamins, Amsterdam, 2019.
Chapter 15. Exploration of the Rhapsodie corpus: Data structure, formats and query tools.
Anne Lacheret-Dujour, Sylvain Kahane, Rachel Bawden, Serge Fleury and Ilaine Wang.
In Rhapsodie – A Prosodic and Syntactic Treebank for Spoken French.
Eds. Anne Lacheret-Dujour, Sylvain Kahane, and Paola Pietrandrea.
John Benjamins, Amsterdam, 2019.
Technical report
Protocole de codage microsyntaxique
Sylvain Kahane, Kim Gerdes, Pietrandrea Paola, Benzitoun Christophe, Rachel Bawden, Marie-Amélie Botalla and Adèle Désoyer (2013).
Translated into English by Rachel Bawden: Protocol for micro-syntactic coding.
Link to the Rhapsodie project website.
Other
[Book Review] Understanding Dialogue: Language Use and Social Interaction
Rachel Bawden (2021).
Computational Linguistics:703–705. MIT press.
Boosting for Model Selection in Syntactic Parsing
Rachel Bawden (2015).
Master's thesis.
Alpage-INRIA.
Supervised by Benoit Crabbé
Supervision
PhD students
Analogy for multilingual NLP.
Co-supervised with Benoît Sagot.
Evaluation of the machine translation
of scientific documents. Co-supervised with François Yvon (CNRS).
Machine translation of scientific
documents. Co-supervised with François Yvon (CNRS).
Robust Neural Machine Translation. Co-supervised with Benoît Sagot.
Multimodal Machine Translation. Co-supervised with
with Ivan Laptev, Benoît Sagot and Cordelia Schmid.
Neural models of language
evolution. Co-supervised with Benoît Sagot and Laurent Romary.
Interns and engineers
Data collection and translation models for a regional language of France (COLaF project)
Domain adaptation for neural machine translation in low-resource settings.
Linguistically inspired language models for closely related languages.
Domain adaptation in NMT.
Contrastive training for NMT models
for lexical disambiguation. Co-supervised with Benoît Sagot.
Investigating the effect of input representations on language sharing in multilingual models.
Exploration of multilingual
and multimodal word embeddings. Co-supervised with Benoît Sagot, Cordelia Schmid and Ivan Laptev.
Automatic tools for improving jurisprudence consistency, Co-supervised with Benoît Sagot and in collaboration with the Cour de Cassation.
Machine Translation of Noisy Texts. Co-supervised with Djamé Seddah.
Improving Low-Resource Neural Machine Translation of Related Languages by Transfer Learning. Co-supervised with Alexandra Birch.
Continuous learning for
Neural Machine Translation from Human
Post-edits. Co-supervised with Alexandra Birch.
Integrating document
structure information into Neural Machine
Translation using cache-based models. Co-supervised with Annie Louis and Bonnie Webber.
Exploiting Predictable Document Substructure in Neural Machine Translation. Co-supervised with Annie Louis and Bonnie Webber.
Teaching Experience
4th year lectures, tutorials and practical classes (30hrs/year)
2nd year practical classes (10hrs)
3rd year tutorials and practical classes (27hrs)
3rd year tutorials and practical classes (24hrs/year)
3rd year tutorials and practical classes (28hrs)
3rd year (12hrs)