@luigi_proc

PhD Student at @SapienzaNLP. Interested in ML and NLP.

 PhD Student
poccio.github.io
Joined October 2017
  • Tweets46
  • Following142
  • Followers82
1Media
So happy about this!
Lightning AI ⚡️
@LightningAI24 Oct 2021
💜⚡️ Sunday Community Spotlight! Classy: A PyTorch-based library for fast prototyping and sharing of deep neural network models github.com/sunglasses-ai/cla… 👏🏽 Kudos to @Valahaar @luigi_proc & edobobo on your work!

GitHub - litus-ai/classy: classy is a simple-to-use library for building high-performance Machine...

classy is a simple-to-use library for building high-performance Machine Learning models in NLP. - litus-ai/classy

github.com
1
7
Luigi Procopio retweeted
SapienzaNLP@SapienzaNLP2 May 2023
#NLPaperAlert: "Entity Disambiguation with Entity Definitions" presented today at #EACL2023 @eaclmeeting By @luigi_proc @ConiaSimone @edoardo_barba @RNavigli @SapienzaNLP Paper: aclanthology.org/2023.eacl-m… #NLProc #AI
1
9
25
2,171
Luigi Procopio retweeted
Julien Chaumond
@julien_c1 Jul 2022
BTW.... dalle-mega from @borisdayma is now openly accessible on @huggingface ⚡️ To download it (10GB): git clone huggingface.co/dalle-mini/da…
23
175
7
1,325
Luigi Procopio retweeted
Roberto Navigli@RNavigli2 Jul 2022
The Rome Workshop on 10 Years of #BabelNet & Multilingual Neurosymbolic Natural Language Understanding will start on Monday with int'l speakers & brainstorming sessions! So excited!!! Register at mousse-project.org @ERC_Research @WikiResearch @SapienzaNLP @babelscape #nlproc
1
13
34
Super happy that our DiBiMT paper got recognized as the Best Resource Paper @aclmeeting #ACL2022! 🥳🎉 A (not so) short 🧵 about it :) 👇 Joint work with @FedeMartelli25 @FrancescoSaina @RNavigli 📜: aclanthology.org/2022.acl-lo… 1/7

DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation

Niccolò Campolungo, Federico Martelli, Francesco Saina, Roberto Navigli. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

aclanthology.org
3
7
2
30
Luigi Procopio retweeted
Simone Conia@ConiaSimone21 Apr 2022
#ACL2022 is only 1 month away!☘️ Happy to share 3 papers I (co-)authored on #SemanticRoleLabeling, #EmotionClassification & #WordSenseDisambiguation! Always a pleasure working with @RNavigli, @MicheleBevila20, @MarcoMaru3, @caesar_one_ & @SapienzaNLP. 🧵Thread [1/n]
1
3
17
Luigi Procopio retweeted
SapienzaNLP@SapienzaNLP14 Apr 2022
#NLPaperAlert 📢 We bring together existing resources, revise them, and propose SRL4E, a unified evaluation on Semantic Role Labeling 4 Emotions! Read our #ACL2022 preprint: researchgate.net/publication… By @caesar_one_ @ConiaSimone @RNavigli + @ERC_Research @EuroLangTech #NLProc
1
13
2
30
Luigi Procopio retweeted
SapienzaNLP@SapienzaNLP6 Apr 2022
Open & commercial Neural Machine Translation models heavily suffer from disambiguation biases! We present DiBiMT, our novel benchmark for lexical-semantic bias in MT at #ACL2022! By @Valahaar @FedeMartelli25 @FrancescoSaina @RNavigli @ELEXIS_EU #NLProc 📝:researchgate.net/publication…
12
2
21
Luigi Procopio retweeted
SapienzaNLP@SapienzaNLP4 Apr 2022
#NLPaperAlert 📢: where do language models encode predicate-argument structure information? And how to use it in multilingual Semantic Role Labeling? Find out more in our #ACL2022 paper! #NLProc 📝: researchgate.net/publication… By @ConiaSimone @RNavigli + @ERC_Research @EuroLangTech
10
20
Check this out, we have added a @spacy_io component for REBEL to perform end2end Relation Extraction. Just import it and add it to your pipeline. Extracting relations has never been this easy! github.com/Babelscape/rebel#…
3
17
54
Luigi Procopio retweeted
SapienzaNLP@SapienzaNLP31 Mar 2022
We analyzed current Word Sense Disambiguation #WSD systems so that you don’t have to 🔍. There is a hard core that no system can solve! 😱 #NLProc Read our #ACL2022 paper: researchgate.net/publication… By @MarcoMaru3 @ConiaSimone @MicheleBevila20 @RNavigli + @ERC_Research @elexis_eu
12
33
Classy is a @PyTorch-based library for the fast prototyping and sharing of deep neural network models. It wraps the best libraries like PyTorch Lightning, Transformers, @streamlit and offers them to users with a simple CLI interface. Try it here: github.com/sunglasses-ai/cla…
17
1
27
Back at #EMNLP2021, while presenting ConSeC, quite a few colleagues asked @edoardo_barba and me “have you tried this extractive formulation on entity disambiguation?” Yes, we were and it’s now an #ACL2022 paper!
SapienzaNLP@SapienzaNLP24 Mar 2022
Extractive Entity Disambiguation is our (@edoardo_barba @luigi_proc @RNavigli) new paper at #ACL2022! Guess what, we perform ED as a Text Extraction task using only Wikipedia Titles and achieve a new SotA in standard and constrained data regimes. @ERC_Research #NLProc Links: ⬇️
3
6
Hey #NLProc, with @edoardo_barba we released the checkpoint of ConSeC trained on SemCor+WNGE (83.2 on ALL!). Feel free to play with it at github.com/sapienzanlp/conse…. Multilingual models and more to come 😉

GitHub - SapienzaNLP/consec: Text Extraction Formulation + Feedback Loop for state-of-the-art WSD...

Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021) - SapienzaNLP/consec

github.com
1
4
10
Hey, #NLProc if I create a library with recent SOTA models for WSD and Entity Linking (implementation and checkpoints). Would you use it?
2
8
1
31
It is here. General release is still scheduled for April 4.
106
826
274
7,530
Last week remote working with @edoardo_barba and @Valahaar: skiing in the Alps while checking runs with @wandb
1
5
2
28
🚨 classy v0.1.0 is out 🚨 You can setup NLP experiments even faster than before, with some cool additional features for free (streamlit demo, prediction, support for custom evaluation)! @Valahaar @luigi_proc and I even wrote the docs 🙄 (thanks @Docusaurus)
1
6
20
.@edoardo_barba & @luigi_proc presenting word sense disambiguation by integrating a feedback loop into a DeBERTA-based model that picks out the right definition. #EMNLP2021 #NLProc
3
14
Load more