Sign in

Marine Carpuat

@marinecarpuat.bsky.social
3.2K followers 243 following 20 posts

Associate Professor in Computer Science at the University of Maryland. Human-Centered Natural Language Processing & Machine Translation

PostsRepliesMedia
Marine Carpuat @marinecarpuat.bsky.social · 18/06/2025
What should Machine Translation research look like in the age of multilingual LLMs? Here’s one answer from researchers across NLP/MT, Translation Studies, and HCI. "An Interdisciplinary Approach to Human-Centered Machine Translation" arxiv.org/abs/2506.13468
arxiv.org
An Interdisciplinary Approach to Human-Centered Machine Translation
Machine Translation (MT) tools are widely used today, often in contexts where professional translators are not present. Despite progress in MT technology, a gap persists between system development and...
1187
Marine Carpuat @marinecarpuat.bsky.social · 16/06/2025
Tell me you're in France without telling me: live news coverage of high school philosophy exams! 2025 Bac de philo questions: - Notre avenir dépend-il de la technique ? - La vérité est-elle toujours convaincante ? - Or discuss an excerpt from Rawls’ Theory of Justice. www.lemonde.fr/campus/live/...
lemonde.fr
En direct, bac de philo 2025. Les réponses à vos questions sur les sujets : « L’épreuve écrite de philosophie valide la capacité des élèves à prendre un peu de recul sur des questions dont la réponse ...
« Notre avenir dépend-il de la technique ? », « La vérité est-elle toujours convaincante ? », ou encore « Avons-nous besoin de l’art ? » en dissertation, John Rawls et Adam Smith en explication de tex...
141
Marine Carpuat @marinecarpuat.bsky.social · 13/06/2025
Disagreement between LLMs can be a strength! @dayeonki.bsky.social shows that having multiple LLMs debate improves their answers to culturally variable social norm questions. #ACL2025
062
Reposted by Marine Carpuat
Dayeon (Zoey) Ki @dayeonki.bsky.social · 21/05/2025
1/ How can a monolingual English speaker 🇺🇸 decide if an automatic French translation 🇫🇷 is good enough to be shared? Introducing ❓AskQE❓, an #LLM-based Question Generation + Answering framework that detects critical MT errors and provides actionable feedback 🗣️ #ACL2025
112
Reposted by Marine Carpuat
Dayeon (Zoey) Ki @dayeonki.bsky.social · 17/04/2025
🚨 New Paper 🚨 1/ We often assume that well-written text is easier to translate ✏️ But can #LLMs automatically rewrite inputs to improve machine translation? 🌍 Here’s what we found 🧵
184
Reposted by Marine Carpuat
Wissam Antoun @wissamantoun.bsky.social · 14/04/2025
ModernBERT or DeBERTaV3? What's driving performance: architecture or data? To find out we pretrained ModernBERT on the same dataset as CamemBERTaV2 (a DeBERTaV3 model) to isolate architecture effects. Here are our findings:
34315
Reposted by Marine Carpuat
Wissam Antoun @wissamantoun.bsky.social · 15/11/2024
CamemBERT 2.0: A Smarter French 🇫🇷 Language Model Aged to Perfection 👌 We release a much-needed update for the previous. SOTA French encoder LM. We introduce two new models CamemBERTa-v2 and CamemBERT-v2, based on the DeBERTaV3 and RoBERTa recipe. So what's new? [1/8]
12010
Reposted by Marine Carpuat
Inria Paris NLP (ALMAnaCH team) @inriaparisnlp.bsky.social · 05/03/2025
We are happy to announce our next seminar, given by Florian Cafiero @floriancafiero.bsky.social (PSL @ecoledeschartes.bsky.social) entitled "A Riddle in a Haystack: Using Large Language Models for the Detection of Rare Phenomena" on Friday 7th March at 11am CET. Details here: t.co/pPbWfkALM4!
Florian Cafiero - "A Riddle in a Haystack: Using Large Language Models for the Detection of Rare Phenomena" - ALMAnaCH seminar 7th March 2025 at 11am CET
193
Reposted by Marine Carpuat
Rock Pang @rockpang.bsky.social · 31/01/2025
🤔 Interested in how #HCI thinks about using #LLMs, or looking to understand best practices for human-LLM interaction? 🚨🚨New paper: Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review 🧵
1177
Reposted by Marine Carpuat
IWSLT @iwslt.bsky.social · 28/01/2025
First up, a new task for 2025: *Instruction-following for speech processing!* Explore instruction-following for speech ⇨ Integrate speech foundation models with LLMs across tasks such as speech translation, recognition, summarization, and QA. 🔗: iwslt.org/2025/instruc...
iwslt.org
Instruction-following Speech Processing track
Home of the IWSLT conference and SIGSLT.
186
Reposted by Marine Carpuat
IWSLT @iwslt.bsky.social · 28/01/2025
We are pleased to announce that our 2025 shared tasks have launched! Find details and data on our website, with evaluation data to be released April 1! iwslt.org/2025/#shared... We will be highlighting one task per day here and the other site. Join us for an exciting year of speech translation!!
iwslt.org
IWSLT 2025
Home of the IWSLT conference and SIGSLT.
032
Marine Carpuat @marinecarpuat.bsky.social · 23/01/2025
I'll be Germany next week to visit TUM Heilbronn and LMU Munich. Looking forward to learning from NLP researchers there and sharing recent work on human centered-machine translation! (And to discovering how much German I can actually understand after 2 weeks on duolingo 😅)
071
Reposted by Marine Carpuat
Gabriele Sarti @gsarti.com · 10/12/2024
Our piece is finally out in the Imminent blog! 🎉It presents preliminary findings of our recent study evaluating the usefulness of word-level quality estimation in real-world post-editing settings (paper forthcoming)! 🧵1/ imminent.translated.com/can-word-lev...
imminent.translated.com
Can Word-level Quality Estimation Inform and Improve Machine Translation Post-editing? - Imminent - Translated's Research Center
Can Word-level Quality Estimation Inform and Improve Machine Translation Post-editing? - % Imminent is Translated’s Research Center which supports companies in localization, funds language data resear...
1259
Marine Carpuat @marinecarpuat.bsky.social · 11/12/2024
ICYMI: the UMD LSC is looking for a postdoctoral fellow with an interdisciplinary research agenda in language sciences. languagescience.umd.edu/news/job-opp... If your interests connect to #NLP research that helps people communicate across languages, please reach out!
languagescience.umd.edu
Job Opportunity: Language Science Postdoc
The Maryland Language Science Center is recruiting an outstanding postdoctoral researcher for our inaugural Fellowship for Postdoctoral Scholars. The goal of the fellowship is to support early-career ...
131
Marine Carpuat @marinecarpuat.bsky.social · 10/12/2024
Interesting to see how Le Monde uses AI: MT (English articles via DeepL + postediting!), TTS, video captioning and translation, proofreading, and experimenting with rewriting content from news agency to their style specs www.lemonde.fr/le-monde-et-...
lemonde.fr
De quelles façons « Le Monde » se sert-il de l’IA ?
Conformément à ses engagements, « Le Monde » publie une liste exhaustive de l’usage par sa rédaction d’outils d’assistance éditoriale relevant de l’intelligence artificielle générative.
071
Reposted by Marine Carpuat
Hellina Hailu Nigatu @hellinanigatu.bsky.social · 02/12/2024
I hope I am not late to the party (was away post-quals chilling) but here are some thoughts on why this is bad IMO: First, a disclaimer that I am writing this as an African who is a speaker of multiple African languages, NLP researcher of African languages, and HCI researcher focusing broadly on..
912560
Reposted by Marine Carpuat
Katya Artemova @katya-art.bsky.social · 27/11/2024
Such a good thread idea! arxiv.org/abs/2305.10284 "Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks" by Anas Himmi et al. They explore ranking LLMs is required where some scores for certain tasks are missing. The Borda count constructs reliable leaderboards.
arxiv.org
Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks
The evaluation of natural language processing (NLP) systems is crucial for advancing the field, but current benchmarking approaches often assume that all systems have scores available for all tasks, w...
021
Marine Carpuat @marinecarpuat.bsky.social · 27/11/2024
What #NLP papers do you wish more people knew about? I'll start: "Toward Machine Translation of Scientific Neologisms", by Lerner & Yvon aclanthology.org/2024.jeptaln... A real task in cross-lingual communication, linguistically grounded, and hard for LLMs! Well worth a read, even through MT!
aclanthology.org
Vers la traduction automatique des néologismes scientifiques
Paul Lerner, François Yvon. Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position. 2024.
5317
Marine Carpuat @marinecarpuat.bsky.social · 12/11/2024
Estimating translation quality is key to building trustworthy machine translation systems, but most work focuses on text. How well can we assess *speech* translation? 🎤 Check out our 𝐒𝐩𝐞𝐞𝐜𝐡𝐐𝐄 💬 paper with Hyojung Han and Kevin Duh at #EMNLP2024! aclanthology.org/2024.emnlp-m...
aclanthology.org
SpeechQE: Estimating the Quality of Direct Speech Translation
HyoJung Han, Kevin Duh, Marine Carpuat. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
261