PhD student at the @GroNlp group of @univgroningen. I work on multilingual and cross-lingual NLP for Dutch and underresourced languages.
Joined April 2018
- Tweets 125
- Following 289
- Followers 251
- Likes 778
6 Photos and videos
Pinned Tweet
24 Feb 2022
Our new @GroNLP paper w/@martijnwieling and @MalvinaNissim, about cross-lingual transfer for >100 languages is accepted by @aclmeeting! We show that English is NOT the best training language and we discuss what factors do influence effective transfer. (Paper models demo code) 1/n
10
46
198
Wietse de Vries (contact me by email) retweeted
13 Dec 2022
After a year of restless development, I'm finally happy to announce Inseq, a new tool to democratize post-hoc interpretability of sequence generation models ๐ github.com/inseq-team/inseq #nlproc #xai
Some highlights ๐ 1/
6
36
165
๐ข๐ฅณ Our group is opening two 2y post-doc positions in NLP in the wider context of Humane AI! Come work with us! All details: rug.nl/let/sectorplan #NLProc
Main gist of the two specific projects below ๐
Interested? Get in touch with @MalvinaNissim
1
19
28
Wietse de Vries (contact me by email) retweeted
9 Jun 2022
Want to know more about our @univgroningen @FacultyofArtsUG @GroNlp #NAACL2022 paper? Check it out in our ๐new๐ video! ๐ฝ๏ธ by the great @musicbyblanks
youtu.be/c5nowiEItA4
8 Apr 2022
Can we distinguish closely-related Dutch regional languages using only 6โฃ seconds of speech? With multilingual pre-training and fine-tuning on Dutch we can! Even more accurately compared to using a (new) monolingual Dutch model. Read it in our new @naaclmeeting paper! ๐
7
19
ALT Members of the Computational Linguistic Group at the University of Groningen posing in front of a "ACL 2022" banner in Dublin after the end of the main conference of the Association for Computational Linguistics.
5
41
Wietse de Vries (contact me by email) retweeted
24 May 2022
Conference season is here!๐ @Wietsedv just presented his paper (with @MalvinaNissim & @martijnwieling, @GroNlp) on cross-lingual transfer for >100 languages at #ACL2022 (@aclmeeting). ๐ If you missed it, you can still catch him at his poster tomorrow!
4
15
๐ "Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages" by @Wietsedv et al. will be presented in session OS4-6 at 12:00 CEST x.com/Wietsedv/status/149678โฆ
24 Feb 2022
Our new @GroNLP paper w/@martijnwieling and @MalvinaNissim, about cross-lingual transfer for >100 languages is accepted by @aclmeeting! We show that English is NOT the best training language and we discuss what factors do influence effective transfer. (Paper models demo code) 1/n
1
1
4
26 Apr 2022
I am a bit confused by the #ACL2022 program. The list of accepted papers shows 699 long short accepted papers (2022.aclweb.org/papers), but the program only shows 289 main ACL papers (mixed oral poster) how did 410 papers vanish?
1
26 Apr 2022
And why are there additionally 129 poster presentations for Findings papers mixed between all other poster presentations? That means that these papers should have been accepted and recognized as main conference papers, right? Am I missing something?
2
Wietse de Vries (contact me by email) retweeted
8 Apr 2022
Can we distinguish closely-related Dutch regional languages using only 6โฃ seconds of speech? With multilingual pre-training and fine-tuning on Dutch we can! Even more accurately compared to using a (new) monolingual Dutch model. Read it in our new @naaclmeeting paper! ๐
3
20
82
Wietse de Vries (contact me by email) retweeted
10 Mar 2022
Our work w/ @MalvinaNissim on the Italian T5 is finally out! IT5 is the first encoder-decoder NLM pre-trained on Italian, advancing the state-of-the-art in many ๐ฎ๐น NLG & NLU tasks.
Paper: arxiv.org/abs/2203.03759
Code: github.com/gsarti/it5
Demo: hf.co/spaces/it5/it5-demo
๐งต๐
ALT A large text on a background with the colors of the Italian flag saying "IT5, a T5 model for the Italian language", with a link to a demo for the model (hf.co/it5/it5-demo)
6
17
98
24 Feb 2022
Our new @GroNLP paper w/@martijnwieling and @MalvinaNissim, about cross-lingual transfer for >100 languages is accepted by @aclmeeting! We show that English is NOT the best training language and we discuss what factors do influence effective transfer. (Paper models demo code) 1/n
10
46
198
24 Feb 2022
I think annotation efforts should focus on (higher-resource) languages from different language families and other clusters that can be identified by other discussed factors. Zero-shot transfer can be a solution for low-resource if there is training data for related languages.
1
1
9
24 Feb 2022
Models and a demo can be found on @huggingface Spaces (second link). Evaluation results for each model can be found on the linked model pages.
๐ Paper: wietsedv.nl/files/devries_acโฆ
๐ค Models Demo: hf.co/spaces/wietsedv/xpos
๐ป Code: github.com/wietsedv/xpos
1
1
15
Our paper in which we ultimately recommend using Wav2Vec2-based acoustic representations to model subjective non-native pronunciation differences, has been accepted by the Journal of Phonetics! Transformers everywhere!
1
5
And just in time for the holidays, exciting news ๐ฅณ: we're hiring! Assistant professorship in CL/NLP, permanent after 18mo if criteria are met. Vibrant atmosphere, great group! See full ad for details and contact bit.ly/CLjob-GroNLP
#NLProc @univgroningen @FacultyofArtsUG
19
28