Minimum Bayes Risk decoding has recently gained momentum in #NLProc.
However, a generic implementation for @huggingface Transformers was missing. Check out our new 𝗺𝗯𝗿 🔥repo, which is designed to work with any model and metric on the Hub: https://t.co/G5QIG0cZFm
Check out our paper on segmentation for sign languages! We are one step closer to being able to provide basic NLP tools for sign languages. Great work by Amit and Zifan!
📣 Our paper on "Linguistically Motivated Sign Language Segmentation" is in for #EMNLP23 Findings. Segmentation? Consider it solved!
w/ @Jiang_Zifan, @bricksdont, @ebling_sarah, and @yoavgo
https://t.co/uCgPh8iILa
It has been shown that MBR decoding significantly outperforms MAP decoding, but its high cost makes it impractical for most applications. Can we harvest the quality gains of MBR at train time w/o sacrificing inference-time efficiency? TLDR: yes!
https://t.co/pGHBGmh12d
🌟 Just published "SignBank+: Multilingual Sign Language Translation Dataset" (w/ @Jiang_Zifan).
Just $500 in dirty dataset cleanup with ChatGPT, leads to a 20-30 BLEU score boost—no changes to the models required.
Check out the paper!
https://t.co/gzY78fCgXi
I'm hiring a post-doctoral researcher to work on multitask/multilingual/multimodal NLP at the University of Zurich. Fully funded until July 2025. Apply by September 15!
https://t.co/5GitmvpszN
Can highly recommend the EASIER Autumn School in Hamburg! Basic idea: teaching sign language to NLP people, and NLP to sign language people. You can apply for fiancial support.
https://t.co/IVZHWyIO4Z
🎉 To learn more about this work catch Amit *today* at #ACL2023, poster session, 15:00-16:30 UTC, Frontenac Ballroom and Queen's Quay!
https://t.co/Cz90fn04na
Want to work on a truly unsolved NLP problem, something that ChatGPT most definitely cannot do? Participate in the the
Second WMT shared task on sign language translation! 1/3