user avatar
UW NLP
@uwnlp
The NLP group at the University of Washington.
Seattle, WA
Joined September 2015
Posts
  • user avatar
    If you're applying for PhD this cycle, this is a great resource, with examples of SoPs from applicants from previous years:
  • user avatar
  • user avatar
  • user avatar
    UWNLP ❤️ BLOOM, which utilizes two UWNLP developments: ALiBi (position embedding that allows models to extrapolate to longer sequences) by @OfirPress et al. bitsandbytes (8-bit optimization) by @Tim_Dettmers et al.
    The Technology Behind BLOOM Training🌸 Discover how @BigscienceW used @MSFTResearch DeepSpeed + @nvidia Megatron-LM technologies to train the World's Largest Open Multilingual Language Model (BLOOM): huggingface.co/blog/bloom-meg…
  • user avatar
    EMNLP is requiring a limitation section (in case anyone missed this):
  • user avatar
    Watch @JonathanBerant's talk on "Latent Tree Models for Compositional Generalization" here: youtube.com/watch?v=VAVIZB…
  • user avatar
    Theory of Mind reasoning remains challenging for language models. Check out FANToM's, a benchmark for ToM in conversations where LLMs still haven't made ~any progress, yet the task is quite easy for humans. Developed by researchers at AI2 & UW!
    ⁉️ Let's check how GPT-4o, Gemini, Llama3, Mixtral, and Claude perform on theory of mind, shall we?🌟We report new results on Benchmark FANToM👻 - GPT-4o tops the chart by finally achieving score of 2.0/100 (vs. Human 87.5) - Huge boost for Gemini-1.5-flash compared to
  • user avatar
    Deep Multitask Learning for Semantic Dependency Parsing from Hao Peng, Sam Thomson and @nlpnoah arxiv.org/pdf/1704.06855…
  • user avatar
    Great work by @wittgen_ball et al.
    Finetuning Pretrained Transformers into RNNs Successfully converts a pretrained transformer into its efficient linear-complexity recurrent counterpart with a learned feature map to improve the efficiency while retaining the accuracy. arxiv.org/abs/2103.13076
  • user avatar
    Too much weight is given to the opinions of three anonymous, over-worked, and poorly incentivized reviewers
  • user avatar
    Hey Everyone! @uwnlp is excited to see everyone starting at @NAACLHLT tomorrow. Our students, postdocs, faculty, and collaborators all published some great research so we hope you’ll come talk to use at our tutorials, talks, posters and workshops! #NLProc
  • user avatar
    It's workshop survey time! Make sure to check out these workshops being organized by UW NLP this year at ACL/NAACL/EMNLP!
  • user avatar
    UW CSE has a mentorship service for PhD applicants and this thread by @jbhuang0604 lists similar programs at other institutions.
    Replying to @jbhuang0604
    *University of Washington CSE: Pre-Application Mentorship Service* cs.washington.edu/academics/phd/…
  • user avatar
    .@nlpnoah's talk about Sequence Models at LxMLS 2020 is at youtube.com/watch?v=e8TVif…