Log inSign up
user avatar
Orhan Firat
@orf_bnw
Research Scientist at Google DeepMind
New York
Joined August 2010
1,126
Following
2,220
Followers
  • user avatar
    Orhan Firat
    @orf_bnw
    Sep 24, 2022
    🎉👏! this made me feel sentimental- was almost gonna dropout of phd after the 2nd time this got rejected! I was so fortunate to have mentors like @kchonyc and Yoshua convincing me otherwise, and ofc collaborators like @caglarml and @imkelvinxu ambitiously pushing this forward 🥹
    user avatar
    Kyunghyun Cho
    @kchonyc
    Sep 23, 2022
    well :) 5 years too late but still happy to receive the best research paper award cc ⁦@orf_bnw⁩ ⁦@caglarml⁩ ⁦@imkelvinxu⁩
  • user avatar
    Orhan Firat
    @orf_bnw
    Jul 12, 2019
    Massively Multilingual NMT in the wild: 100+ languages, 1B+ parameters, trained using 25B+ examples. Check out our new paper for an in depth analysis: arxiv.org/abs/1907.05019 #GoogleAI
    arXiv logo
    arxiv.org
    Massively Multilingual Neural Machine Translation in the Wild:...
    We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a...
  • user avatar
    Orhan Firat
    @orf_bnw
    Dec 10, 2019
    How to build 1000+ layer Transformers with 80+ billion parameters? By using GPipe 🙂 We will be presenting GPipe today @NeurIPS - East Exhibition Hall B+C at poster #40 Paper > arxiv.org/abs/1811.06965 Poster and Slides > nips.cc/Conferences/20… (1/4)
    arXiv logo
    arxiv.org
    GPipe: Efficient Training of Giant Neural Networks using Pipeline...
    Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks. In many cases, increasing model capacity...
  • user avatar
    Orhan Firat
    @orf_bnw
    Dec 7, 2023
    And in a few hours, I will be discussing Gemini’s multilingual capabilities at MRL @mrl2023_emnlp #EMNLP2023 . I will trace our path from M4, PaLM, PaLM 2, and Gemini through the lens of multilinguality; share some lessons learned and open problems. Exciting!
    user avatar
    MRL
    @mrl2024_emnlp
    Dec 6, 2023
    Are you excited like us for our workshop tomorrow? We hope you are. Check out the updated schedule on our website with location details and full list of papers: sigtyp.github.io/ws2023-mrl.html
    28K
  • user avatar
    Orhan Firat
    @orf_bnw
    Dec 7, 2023
    ♊️Gemini 1.0 is here 🚀- polymath and polyglot LLM! Proud to be part of this amazing team!
    user avatar
    Jeff Dean
    @JeffDean
    Dec 6, 2023
    I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks,
    8.8K
  • user avatar
    Orhan Firat
    @orf_bnw
    Jul 19, 2022
    Thrilled to be @#ICML2022 in person! ⬇️ Some work we will be presenting around large language models: 1⃣understanding scaling properties under different architecture biases,2⃣ interplay b/w data/noise/architecture and 3⃣ efficient in-context learning w/ sparse models (GLaM-1.2T)
  • user avatar
    Orhan Firat
    @orf_bnw
    Feb 11, 2020
    Do massively multilingual translation models (M4) generalize to cross-lingual downstream tasks? Check out Poster #218 today #AAAI2020. Presented by @asiddhant1 with the awesome team Melvin Johnson, @naveenariva, Jason Riesa, @ankurbpn Paper arxiv.org/pdf/1909.00437… Poster 👇1/2
  • user avatar
    Orhan Firat
    @orf_bnw
    May 3, 2021
    This week we will be presenting three papers at #ICLR2021 each exploring a different aspect of multi-task/multilingual models at scale: (1) modeling (2) optimization and (3) large scale systems.
  • user avatar
    Orhan Firat
    @orf_bnw
    Oct 14, 2019
    Summary of our recent work on multilingual NMT. We mainly studied scaling up the models on two axes simultaneously: number of languages and the size of the neural networks. Several artifacts along the way: ...
    user avatar
    Google AI
    @GoogleAI
    Oct 11, 2019
    New research demonstrates how a model for multilingual #MachineTranslation of 100+ languages trained with a single massive #NeuralNetwork significantly improves performance on both low- and high-resource language translation. Read all about it at: goo.gle/325DlY4
    GIF
  • user avatar
    Orhan Firat
    @orf_bnw
    Sep 25, 2020
    More on confluencing unsupervised and multilingual MT. Great work with the awesome team: @xgarcia238, @ank_parikh , @adisid01, @Foret_p, @ThiboIbo of @GoogleResearch, #GoogleAI (1/3)
    user avatar
    Ankur Parikh
    @ank_parikh
    Sep 24, 2020
    Check out our multilingual unsupervised translation work! Theory + SOTA results. Led by @xgarcia238 (1/4) 1. Multilingual View of Unsupervised MT - Findings of EMNLP 2020 (arxiv.org/abs/2002.02955 ) 2. Multilingual Unsupervised MT for Rare Languages (arxiv.org/abs/2009.11201 )
  • user avatar
    Orhan Firat
    @orf_bnw
    Oct 22, 2020
    First step towards "bit/pixel level", end-to-end neural machine translation. Led by awesome @elmanmansimov and Mitchell Stern @GoogleAI Let's see where does vision end and language start, or is there even a distinction between the two? Exciting times ahead 🙃
    user avatar
    Elman Mansimov
    @elmanmansimov
    Oct 22, 2020
    During summer 2019, together with Mitchell, @orf_bnw, @MiaXuChen, Jakob & Puneet at Google, we worked on an ambitious way of tackling in-image translation (translate text in the image and generate the same image with translated text) using the end-to-end neural approach. [1/2]
  • user avatar
    Orhan Firat
    @orf_bnw
    Sep 14, 2019
    More on massively multilingual NMT. This time we analyze the representational similarity across languages, how they evolve across layers and how robust are they. Great analysis and intriguing results are thanks to the great work by @snehaark. More to come, very soon ...🙂
    user avatar
    Sneha Kudugunta
    @snehaark
    Sep 13, 2019
    New EMNLP paper “Investigating Multilingual NMT Representation at Scale” w/ @ankurbpn, @orf_bnw, @caswell_isaac, @naveenariva. We study transfer in massively multilingual NMT @GoogleAI from the perspective of representational similarity. Paper: arxiv.org/pdf/1909.02197… 1/n
  • user avatar
    Orhan Firat
    @orf_bnw
    Aug 3, 2021
    Today we will be hosting a Machine Translation Birds of a Feather Meetup together with @kchonyc at #ACL2021NLP @aclmeeting come say hi 🙂 at Gather Town D&I Session Room, MT Table (bottom left) - 6pm ET