José G. C. de Souza (@accezz) header
José G. C. de Souza (@accezz) profile picture

PhD, Computer Science, Multilingual NLP and LLMs, Generative AI, Machine Translation, Machine Learning | Ex- @Unbabel, @eBay, PhD @UniTrento / @FBK_research

Lisbon, Portugal
Joined April 2008
Photo by José G. C. de Souza (@accezz)
José G. C. de Souza retweeted
🚀 Thrilled to present our QUEST poster at #NeurIPS2024 in Vancouver! 📅 Thursday, Dec 12th | 4:30-7:30 PM PST 📍 East Exhibit Hall A-C #3108 Looking forward to engaging discussions & connecting with fellow researchers! Stop by to learn more about our work. Joint work with @swetaagrawal20 @tozefarinhas @RicardoRei7 @accezz @andre_t_martins 🔗 Details: neurips.cc/virtual/2024/post… questdecoding.com
4
1
12
2,693
José G. C. de Souza retweeted
Today we release EuroLLM-9B: the best EU-made multilingual LLM of its size! Check the blog post for more info and results: huggingface.co/blog/eurollm-…. Stay tuned for the technical report and bigger and more powerful models!
4
24
9
85
14,011
Super happy with this new product based on our Tower models we have been developing in the last year! Try it out and let us know what you think and what could be improved! wind.ai
💥 Today we’re excited to announce the launch of hubs.li/Q02Y2GpL0 - our new standalone AI solution built for businesses looking to scale quickly with cost-effective translations you can trust. 👇 Learn more about Widn and try it for free. hubs.li/Q02Y2G4q0
4
187
José G. C. de Souza retweeted
Today we release the first EuroLLM paper and models: EuroLLM-1.7B and EuroLLM-1.7B-Instruct! The EuroLLM project will develop open-weight multilingual LLMs that understand and generate text in all official EU languages. Stay tuned for the bigger and stronger EuroLLMs (9B, 22B)!
3
18
7
76
13,438
José G. C. de Souza retweeted
I’m super proud to announce that our Tower 🗼 paper was accepted at COLM 24! To celebrate, we are releasing a new version of TowerInstruct based on Mistral 7B: it achieves similar performance to our 13B model, while being almost half the size! COLM Paper: openreview.net/pdf?id=EHPns3…
1
13
3
46
11,433
José G. C. de Souza retweeted
We offer this 1y postdoc to work with us on the @UTTERProject EU project on LLM-based agents ! Come work with us on 1 or several of these topics: i] managing uncertainty and ambiguity ii] improving the use of conversational context iii] ensuring the safety and alignment of LLMs.
9
13
1,573
José G. C. de Souza retweeted
The Chat Shared Task (WMT2024) is live! 💥💥 Happy to announce this year’s Chat Shared Task which aims to translate a corpus composed of genuine bilingual conversations from the customer support domain!
1
9
13
1,797
Super happy to share something we have been working on lately: TowerLLM, a multilingual model geared towards cross-lingual and translation-related tasks. It has very good performance on translation benchmarks and supports 10 languages.
Introducing Tower our cutting-edge multilingual #LLM for translation-related tasks! 🚀 With 7B parameters and support for 10 languages, Tower dominates in pre-translation tasks and machine translation. 🌎 Explore the future of #NLP now 👉 hubs.li/Q02g7_9B0
1
2
36
2,220
We are releasing: * TowerBase, a continued pre-trained LLaMA2 * TowerInstruct, a finetuned TowerBase on a curated instruction set * TowerBlocks, the instruction set used for TowerInstruct huggingface.co/collections/U…
2
1
123
José G. C. de Souza retweeted
Steering Large Language Models for Machine Translation with Finetuning and In-Context (virtual poster) with @duartealves @nunonmg @JoãoAlves @josepombal @RicardoRei7 @accezz @andre_t_martins Do not hesitate to pass by the poster and say hi to Duarte !
1
5
24
1,800
José G. C. de Souza retweeted
Excited to share that we've won the prestigious #QualityEstimation shared task at #WMT23 for a 2nd year in a row!🎉 Our winning build was a LLM QE system with 11B parameters -- the largest #QE system ever built. 💪 Check out the win here >> hubs.li/Q021rMgZ0 @machtranslate
1
1
6
1,201
Old-ish news but this paper is *so good*. It does such a thorough and systematic comparison of, like, every conceivable setting you could use for n-best reranking or MBR. Extremely useful for figuring out what actually works.
Tired of beam search and all the heuristics needed to make it work well in MT? In our work accepted at #NAACL2022 (co-lead @tozefarinhas) we explore an alternative decoding method that leverages neural metrics to produce better translations! arxiv.org/abs/2205.00978 1/14
4
18
5,638
José G. C. de Souza retweeted
UTTER User Day Update! 🚀 Don't miss the panel on Multimodal LLMs and the Future of NLP Research, moderated by @andre_t_martins. The panelists include @alexandrabirch1, @carolscarton, @slippylolo, and @Turchi_Marco. Secure your spot here: lnkd.in/djBg7Ume #UTTERUserDay
10
1
9
2,960
José G. C. de Souza retweeted
Improving Machine Translation Evaluation with COMET v2.0 - Say Goodbye to Outdated Metrics! 🌟 With all the hype around GPT-4 is more important than ever to have reliable evaluation metrics and methodologies. That why we are excited to release COMET v2.0: resources.unbabel.com/r-d-bl…
4
15
1
39
3,034
José G. C. de Souza retweeted
Does your (EU) country attract or lose top researchers? AT, CH attract a lot. FR, DE, BE, ES are open places: as many leave as arrive. IE is a closed system. Italy, there is something very wrong: *very* few come, many go. Plot made with @ERC_Research data.
60
1,166
191
4,219
Stop by to know more about the Chat shared task and our approach to it!
Replying to @andre_t_martins
7) Thu 16:00–17:30 at #wmt2022: (Poster) Unbabel-IST at the WMT Chat Translation Shared Task - João Alves, Pedro Henrique Martins @accezz @amin_farajian @andre_t_martins
4
If you want to know more about how to combine COMET and Kiwi to get top performance on quality estimation, stop by our poster soon at WMT!
Replying to @andre_t_martins
5) Wed 16:00–17:30 at #wmt2022: (Poster) CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task - @RicardoRei7 @MarcosTreviso @nunonmg @chryssaZrv @CatarinaFarinh7 Christine Maroti @accezz @glushkovato Duarte Alves Luisa Coheur @alonlavie @andre_t_martins
1
4
Want to know more about the latest COMET model which got top performance on the Metrics shared task? Come to see our poster!
Replying to @andre_t_martins
4) Wed 16:00–17:30 at #wmt2022: (Poster) COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task - @RicardoRei7 @accezz Duarte Alves @chryssaZrv @CatarinaFarinh7 @glushkovato @alonlavie Luisa Coheur @andre_t_martins
1
Come to see our poster on data augmentation for MT quality estimation, tackling specifically critical errors related to five different phenomena on three different languages.
Replying to @andre_t_martins
3) Wed 16:00–17:30 at #wmt2022: (Poster) Robust MT Evaluation with Sentence-level Multilingual Augmentation - Duarte Alves @RicardoRei7 @CatarinaFarinh7 @accezz @andre_t_martins