Haitian Sun

PhD student @CarnegieMellon @mldcmu. Former research scientist at @Google Research. NLP & ML.

[Minji Yoon @MinjiYoon90]

@GoogleAI introduced KTN (Neurips'22), my last summer intern project, in their blog today.

Check out how we teach old labels new tricks in heterogeneous graphs 🧙‍♀️ TLDR; we transfer knowledge across multi-modal complex ecosystems using connectivity information🪄

[Ruochen Zhao @RuochenZhao3]

Mistakes of Microsoft's New Bing: Can ChatGPT-like Generative Models Guarantee Factual Accuracy?
Has anyone noticed that the demoed new Bing + ChatGPT was so wrong that it fabricated an entire fiscal report? Read more: https://t.co/RteB1MfuUp

[William Cohen @professorwcohen]

A message to NLP researchers at Twitter - take heart, maybe this is just a signal that it's time to make a change! My research group in Google Pittsburgh is hiring - it's a great place to live and work! #ElonHasNotBoughtUsYet

[Machine Learning Dept. at Carnegie Mellon @mldcmu]

Are you an undergraduate, master's or PhD student? Want to spend next summer at @SCSatCMU researching how to make machine learning systems more robust, transparent, fair, and adaptable to real world problems? Apply for our 2022 summer internship!

https://t.co/YnmeAI2kWw

[Haitian Sun @sun_haitian]

A very interesting dataset with questions that require a “real” reasoning process and have **conditional** answers. Check it out at https://t.co/m1TD8BVBE8

[Russ Salakhutdinov @rsalakhu]

Many real world questions can’t be answered deterministically. Instead, answers can only be true if certain conditions apply.

Check out our new dataset ConditionalQA: an extremely challenging but super exciting task!

Dataset https://t.co/9ZGzOrOopJ
Paper https://t.co/2bBpnUO1Gv

[Bhuwan Dhingra @bhuwandhingra]

Excited to organize the 2nd workshop on Unstructured & Structured KBs (USKB) @ #AKBC2021 with @pat_verga, @sewon__min, Rajarshi Das, @nfitz, Aleksandra Piktus and Siamak Shakeri.

[Graham Neubig @gneubig]

As an experienced NLP researcher, I think this is really good advice that anyone getting into the field should know.

Also as an experienced NLP researcher, problems that seem unsolvable and have no good data or evaluation are maybe the most fun 😃

[Machine Learning Dept. at Carnegie Mellon @mldcmu]

Are you interested in pursuing a graduate program with a focus on machine learning and AI?

Learn more → https://t.co/ZaJjsBbHfU

#MachineLearning #ML #ArtificialIntelligence #AI #DeepLearning #mldcmu #CarnegieMellon #Research #CMUAI

[Yan Liu @yanliu_usc]

ICLR 2022 call for paper is out: https://t.co/qr8nRgSBZ3. If you are interested in serving as a reviewer for ICLR 2022, please sign up at https://t.co/rIS0N4ei4A @iclr_conf.

[Haitian Sun @sun_haitian]

Many thanks to my wonderful collaborators @pat_verga and Bhuwan Dhingra, and my advisors @rsalakhu and @professorwcohen .

[Russ Salakhutdinov @rsalakhu]

Open Predicate Query Language (OPQL): constructing a virtual knowledge base (VKB) that supports KB reasoning & open-domain QA, tackling the incompleteness of knowledge bases by constructing a virtual KB only from text:

https://t.co/UIGOoyQImT

w/t @sun_haitian et. al., #ICML2021

[Russ Salakhutdinov @rsalakhu]

Open Predicate Query Language (OPQL): constructing a virtual knowledge base (VKB) that supports KB reasoning & open-domain QA, tackling the incompleteness of knowledge bases by constructing a virtual KB only from text:

https://t.co/UIGOoyQImT

w/t @sun_haitian et. al., #ICML2021

[Haitian Sun @sun_haitian]

We will present our paper "Adaptable and Interpretable Neural MemoryOver Symbolic Knowledge" at session 10E (Tuesday, 10:10PM EST) #NAACL2021. Join us and discuss wonderful ideas!

Find our paper at: https://t.co/MUKNqbVZuq

[Bill Yuchen Lin @billyuchenlin]

Our #NAACL2021 paper about 𝙤𝙥𝙚𝙣-𝙚𝙣𝙙𝙚𝙙 𝙘𝙤𝙢𝙢𝙤𝙣𝙨𝙚𝙣𝙨𝙚 𝙧𝙚𝙖𝙨𝙤𝙣𝙞𝙣𝙜 will be presented at Session 13B (Wed, 10:20AM PDT). 🎈See you (virtually) then! The paper📄, code💾, data📂, docs 📃, slides🖼️, and etc. are on our website: https://t.co/QjdoLfbmQq