Tommaso

Computer alchemist at Bloomberg Interested in semantics and multilinguality. Opinions are my own.

[Tommaso @pasini_t]

@dlwh Just applied for the channel :) thanks

[Tommaso @pasini_t]

@Customer6_team This is unacceptable considering the cost of a business ticket!!

[Tommaso @pasini_t]

@ITAAirways I’m a business class flyer flying from Dakar and your desk is not open 3 hours before as you suggest and with no online check in available, there is no way we can wait in the lounge. Your client service desk is empty. There is no way to reach out to you. Unacceptable

[Tommaso @pasini_t]

@Customer6_team To continue, business tickets do not allow you access to the Odysse lounge (that I had to pay out of my pocket) nor the topkapi lounge (as of today according to their staff). However your website clearly state those are the ones reserved for your clients.

[Riccardo Orlando @RiccardoRicOrl]

👀 Exciting News! 👀
Happy to announce our latest research paper, “Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget”, will be presented at #ACL2024! 🚀

Try it out! https://t.co/xJzHlNfEzA

Thread below 👇

[UNRWA @UNRWA]

"Are we going to die?"

📍#GazaStrip The situation is unbearable. These are the messages we’re receiving.

Our colleagues - our friends - struggling to explain what is going on to their children.

#HearTheirVoices

[Tommaso @pasini_t]

@DAIRInstitute yet another example …

[Tommaso @pasini_t]

@elonmusk @unusual_whales Ask truthGPT

[Tommaso @pasini_t]

@danielbloureiro Well deserved! Enjoy the drinks!

[Tommaso @pasini_t]

@joabingel @edoardo_barba

[317070 @317070]

Did you know, that you can build a virtual machine inside ChatGPT? And that you can use this machine to create files, program and even browse the internet? https://t.co/15IwHwr2on

[Mike Lewis @ml_perception]

New paper in Science today on playing the classic negotiation game "Diplomacy" at a human level, by connecting language models with strategic reasoning! Our agent engages in intense and lengthy dialogues to persuade other players to follow its plans. This was really hard! 1/5

[Tommaso @pasini_t]

@tallinzen @boknilev Yeah… ACL on this regard sucked … really, 1.5k scientists and no all you can drink coffee?? What was that?

[Tommaso @pasini_t]

@boknilev Inflation is real xD I feel like ACL confs are getting a bit too expensive compared to previous years

[Gerasimos Lampouras @glampouras_NLP]

If attending #acl2022nlp in person and fancy blast-from-the-past #nlg, come by our poster between 15:15 - 16:15: "Hierarchical Recurrent Aggregative Generation for Few-Shot NLG" with @GiulioZhou and @iiacobacNLP.
Paper/talk links:
https://t.co/rz8GY8ZGlm
https://t.co/sUA037aoTv

[Ilias Chalkidis @KiddoThe2B]

“FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing” with @pasini_t, S. Zhang, L. Tomada, @schwemer, and A. Søgaard - poster on Monday 23 PS3-2 17-18h and orally presented on Wednesday 25 OS6-6 10h45-12h15 3/6
https://t.co/abnbJmbQ8V

[Niccolò Campolungo @Valahaar]

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

📜: https://t.co/MJI13hgOID

1/7

[Michele Bevilacqua @MicheleBevila20]

New work on autoregressive language models for retrieval!

We train our model, SEAL (Search Engines with Autoregressive LMs) to produce text snippets occurring somewhere in the corpus, in relevant documents. We use the generated ngrams to rank documents in the corpus.

Thread 👇

[Rexhina Blloshmi @rexhina_b]

I [experiencer] am happy [cue] for @caesar_one_’s first paper in #ACL2022 [stimulus] 🤓 #NLProc

[Tommaso @pasini_t]

@yoavgo Having a tool like twitter fully managed and controlled by one person only is quite scarry to me tbh. Especially if that person is Musk