Tom Kwiatkowski

Research Scientist @ Google

[Tom Kwiatkowski @tmkwiat]

@infoxiao @giansegato 😶

[Tom Kwiatkowski @tmkwiat]

@KerenGu @GoogleDeepMind Keren, you deserve it. We're incredibly sad to see you go but excited to see what you get up to next (after the self care). Please stay in touch.

[Google AI @GoogleAI]

Current retrieval paradigms are complex, pipelined systems. Visit the #EMNLP2023 Google booth today at 10:30 AM to learn about 1-Pager, a system that aligns retrieval and reasoning as a unified task with a single Transformer-based model and decoding pass.

[Livio Baldini Soares @liviobs]

@palak_jain_14 and I will be presenting our 1Pager work soon at the Google research booth at #EMNLP2023. Drop by for a casual chat about this work or working at Google.
https://t.co/vHobHOOG3E

[Sebastian Ruder @seb_ruder]

Check out our work on Evaluating and Modeling Attribution for Cross-Lingual Question Answering presented by @ben_mlr and @liviobs at #EMNLP2023

https://t.co/vcGFnPntCa

[Livio Baldini Soares @liviobs]

Interested in fast and efficient retrieval? Want to use modern LLMs, but don't have the accelerator budget to deal with volume of queries?

Introducing "NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders" at #EMNLP2023

🧵

https://t.co/hIRWW53RkQ

[palak jain @palak_jain_14]

Excited to present "1-Pager" at #EMNLP2023 findings - the first QA system to retrieve evidence and generate answer with a single Transformer model and single decoding pass.
https://t.co/6wdkXOqlEu
Joint work w/ @liviobs @tmkwiat at Google.

[Tom Kwiatkowski @tmkwiat]

@yoavgo Do we have to read the paper first?

[Masakhane @MasakhaneNLP]

Looking to create an NLP dataset for your African language but not sure where to start 🤔?
Well, apply to the Lacuna Fund Masakhane Mentorship program and let us help you get started on your application 🤗🔥!
Let's build together 💪❤️💃🌍! Apply here: https://t.co/bHAPvHqHuk

[Milind Tambe (Moved @milindtambe-ai.bsky.social) @MilindTambe_AI]

Applications now open for pre-doctoral positions at @GoogleAI India! #predoc
https://t.co/TrlY6B6vPP

My team is looking for predocs in #AIforSocialGood: advancing AI/ML for public health & conservation

Spend two years with cutting edge AI projects & amazing mentors in our lab!

[Karol Hausman @hausman_k]

There is a new format for @GoogleAI (Brain) internships:
1) If you are in your final year, apply for an internship: https://t.co/1xpuRxklLV
2) If you are at the beginning of your PhD, apply for a student researcher position: https://t.co/O2ykyZCHzR

[Tom Kwiatkowski @tmkwiat]

@yoavgo Quite. Every time we hire a linguist, the numbers become more meaningful.

[Partha Talukdar @partha_p_t]

#chaii2021, a QA research challenge in Hindi and Tamil, is now live. You can participate even if you didn't pre-register.

https://t.co/GUc7X6HHVP

Build models and data, win prizes, and advance #IndicNLP!

#NLPforAll @GoogleAI @GoogleIndia

[Eunsol Choi @eunsolc]

TACL paper, to be presented at @NAACLHLT tmr!
When sentences appear in a document, they use pronouns and implicit arguments whose meaning is obtained from the broader context. Given a sentence and a context, can we re-write the sentence so that it can stand alone? [1 / 4]

[Sebastian Gehrmann @sebgehr]

Introducing 💎GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. We are organizing shared tasks for our ACL 2021 workshop - Please consider participating!

Website: https://t.co/TAs4F40mga
Paper: https://t.co/VWdcdNv6iu

#NLProc

🧵1/X

[Sewon Min @sewon__min]

Happy new year! #NeurIPS2020 EfficientQA organizers, together with participants, wrote a paper that includes systems, analyses, and lessons learned from the competition. https://t.co/cLYuLoD1Bt

Thanks to everyone who took part in it!

[Tom Kwiatkowski @tmkwiat]

If you're attending #NeurIPS2020, check out our presentation of the awesome EfficientQA competition results, as well as a showdown between the best submissions and some (human) trivia experts.

[Akari Asai @AkariAsai]

Knowledge is not uniformly distributed across languages so an ideal open-retrieval QA model should search and retrieve multilingual resources.
We propose a new task 𝐗𝐎𝐑 𝐐𝐀 with a new dataset 𝐗𝐎𝐑-𝐓𝐲𝐃𝐢 QA(40k newly annotated Qs in 7 languages)
https://t.co/xMUeh2lNHT����

[Ian Tenney @iftenney]

Check out our blog post about the Language Interpretability Tool, an open-source platform for NLP model visualization and analysis. Built with 🔥, from Google's PAIR and Language teams.

[Tom Kwiatkowski @tmkwiat]

@egrefen @facebookai @ucl_nlp Hey Ed, I'm afraid the unrestricted leaderboard above is missing some submissions that were executed outside of our servers. Facebook was beaten out by just two answers: https://t.co/XuNbAcDtrp

Amazing work from Facebook, nonetheless. I look forward to hearing about it.