home.social

#acl2023 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #acl2023, aggregated by home.social.

fetched live
  1. Maybe at the Nobel lecture we'll finally find out how many legs Hinton's cat really has... #acl2023 #throwback @7c0h 😂 nobelprize.org/prizes/physics/

  2. GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration (#ACL2023 demo)

    aclanthology.org/2023.acl-demo

  3. 🥰 Martha Palmer, of lexical semantics in #nlproc fame and one of my profs at Penn, won the #ACL2023 lifetime achievement award. 💪
    Seeing a female prof in computer science was hugely important for me 20 years ago (and continues to be now). #acl2023nlp

  4. Fantastic keynote by Alison Gopnik at #acl2023nlp , arguing that we should see large language models as a new cultural technology (think printing press, internet search) and not new kinds of (intelligent or not) agents #ACL2023 #llm

  5. See the sheer joy of my collaborators at #ACL2023 when 🤩
    DissentQA
    won best Paper AC award

    This is a happy outcome of the fruitful collaboration with a group of wonderfully friendly people

    arxiv.org/abs/2211.05655
    #nlproc #machinelearning #Qa #factuality

  6. Presenting Riveter 💪, a Python package to measure social dynamics between personas mentioned in text.

    Given a verb lexicon, Riveter 💪 can extract entities and visualize relationships between them.

    Package: github.com/maartensap/riveter-

    Paper: maartensap.com/pdfs/antoniak20

    Video: youtube.com/watch?v=Uftyd8eCmF

    Demo Notebook: github.com/maartensap/riveter-

    With Anjalie Field, Jimin Mun, Melanie Walsh, Lauren Klein, Maarten Sap

    #ACL2023 #DH2023 #CulturalAnalytics #DigitalHumanities #NLProc

  7. CW: work, language models, psycholinguistics

    psycholinguistic measures sure correlate with outputs of language models -- I've shown this as have a thousand different people. 90% of the computational modeling track at #ACL2023 is about this these days. it's less about informing psycholinguistic theory but what can correlations get you?

  8. This is great news from ACL 2023:

    2023.aclweb.org/registration/d

    Discounted virtual registration ($0-100) for people attending from regions where ACL registration fees are out of reach.

    Please spread the word! Applications due June 28.

    #NLP #ACL2023

  9. 📢 Excited to share our new #acl2023 Findings paper! #nlp #nlproc

    We introduce NeQA, a dataset consisting of questions with negation, in which language models exhibit inverse, U-shaped, or positive scaling, depending on prompting methods or model families.

    arxiv.org/abs/2305.17311

    🧵

  10. Do I have any friends in #Toronto #TO who I could stay with for a couple days of the #ACL2023 workshops? I arrive the 12th and leave the 14th so just two nights of my dumb ass. I'll buy you any snacks you desire

  11. It is a little bit difficult at the moment to get excited about planning a trip to Toronto.

    #ACL2023

  12. The revised version is now up on arXiv at arxiv.org/abs/2305.03132
    Code and dataset : github.com/CompNet/conivel/tre
    See you at !

  13. Two UKP papers have been accepted to *SEM 2023, which will happen July 13-14 as part of #ACL2023! Read the pre-prints here:
    arxiv.org/abs/2211.01874
    arxiv.org/pdf/2205.06733

    Congratulations to the authors Tilman Beck, Andreas Waldis, Dominic Petrak, Nafise Sadat Moosavi and Iryna Gurevych!

    #SEM2023 @sheffielduni @hslu_luzern

  14. Our paper "The Role of Global and Local Context in Named Entity Recognition" got accepted into ! Preprint: arxiv.org/abs/2305.03132

  15. Thrilled to announce that our work on a new data efficient sota LM for French, #CamemBERTa, has been accepted to #ACL2023 Findings :) @bensagot and I are very excited for @wissam_antoun, it's his first ACL paper!
    code : gitlab.inria.fr/almanach/Camem paper: gitlab.inria.fr/almanach/Camem

  16. Next, in Findings of ACL, there's "CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding" by Yijiang River Dong, myself, & @ccb

    I've mentioned this work before, but now it's published! Here, we used code-based #LLMs like Codex (RIP) to provide structure in story understanding, which we saw helps the LLM figure out what characters are doing better!

    arxiv.org/abs/2212.10754

    2/2 #ACL2023

  17. Yay! 2/2 papers accepted at #ACL2023 !

    First, in the main conference, there's
    "FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information" by @zhuexe, Karmanya Aggarwal, Alex Feng, myself, & @ccb

    Contributions:
    - A corpus of data from people playing #DnD on Discord using a bot called #Avrae, made by @zhuexe himself. Avrae tracks vital game state information for D&D.
    - #LLMs "translating" Avrae commands into plain English.

    arxiv.org/abs/2305.01528

    1/2

  18. On #twitter we've been having a discussion of the #ACL2023 review form, especially the new "excitement" and "soundness" scoring vs. the traditional "recommendation" scoring twitter.com/asayeed/status/163

  19. We need to re-think in-person conferences. Is hybrid alone enough? What about local satellites? #acl2023 #assets2023 #participation Visa processing times exclude people from conferences

    2023.aclweb.org/blog/visa-info

  20. Writing the "Limitations" section for an #ACL2023 submission feels a bit like scripting the text for Reviewer 2.

  21. 1. Don't accept reviewing without carefully checking your calendar

    2. Don't be late with your reviews without notifying ACs on time

    3. Don't ignore ACs

    4. Don't be late again to a new set date

    5. Don't disappear when the discussion starts

    #ACL2023

    1/