Skip to content

Neural Machine Translation (NMT)

Home » Neural Machine Translation (NMT)
  • Where to find me next: ByteClub.ai, LemkoTran, Rusynator, Tokyo and Kraków

    Where to find me next: ByteClub.ai, LemkoTran, Rusynator, Tokyo and Kraków

    1–2 minutes

    Making space for Sanskrit, yoga and good company. Join ByteClub.ai, try LemkoTran.com and Rusynator.com, and hit me up if you’re in Tokyo or Kraków.

  • From a DC Detective Agency to the Google Translate Project: How I Became a Localization Engineer

    From a DC Detective Agency to the Google Translate Project: How I Became a Localization Engineer

    1–2 minutes

    Before neural machine translation, there was a detective agency in a DC skyscraper. Then a decade on the road as a localization engineer, ending at the Google Translate project in 2016.

  • Ahoy, I’m Petro Orynycz, AI Engineer: Apps for Indigenous Languages like Lemko (aka Rusyn)

    Ahoy, I’m Petro Orynycz, AI Engineer: Apps for Indigenous Languages like Lemko (aka Rusyn)

    3–4 minutes

    Ahoy, mateys. I’m Petro Orynycz, an AI engineer from Washington, DC, now between Tokyo and Kraków, building the first neural translators for Lemko and Rusyn. Here is who I am and what ByteClub.ai is about.

  • Lemko Translator App Shipped (Payments Live)

    1–2 minutes

    Mon, Feb 23, 2026 — quick dispatch. After a multi-year grind, the Lemko translator app is shipped and payments are live end-to-end. International Mother Language Day just passed, which hit with perfect timing. It’s a reminder that language tech isn’t only about “big languages” — low-resource and heritage languages deserve serious tooling too. Next step:…

  • Citation in TalaMT: Multilingual Machine Translation for Cabécar-Bribri-Spanish (Jones et al., MRL-WS 2023)

    Citation in TalaMT: Multilingual Machine Translation for Cabécar-Bribri-Spanish (Jones et al., MRL-WS 2023)

    1–2 minutes

    Say It Right: AI Neural Machine Translation Empowers New Speakers To Revitalize Lemko cited in December 2023 by Jones and Coto-Solano of Dartmouth College, as well as González Campos of University of Costa Rica in TalaMT: Multilingual Machine Translation for Cab.car-Bribri-Spanish in the Proceedings of the 3rd Multilingual Representation Learning Workshop in Singapore.

  • Winning Hearts & Tongues: A Polish to Lemko Case Study (2023)

    Winning Hearts & Tongues: A Polish to Lemko Case Study (2023)

    23–35 minutes

    When minority and local languages are lost, national security suffers: not only are significant increases in suicidality, depression, diabetes, assault, and substance abuse often documented, a void is created that has historically been exploited by adversaries. For example, millions from minority language communities ahistorically assume the Russian language and/or identity as their own…

  • BLEU Skies for Endangered Language Revitalization: Lemko Rusyn and Ukrainian Neural AI Translation Accuracy Soars (2023)

    BLEU Skies for Endangered Language Revitalization: Lemko Rusyn and Ukrainian Neural AI Translation Accuracy Soars (2023)

    15–22 minutes

    Abstract Accelerating global language loss, associated with elevated incidence of illicit substance use, type 2 diabetes, binge drinking, and assault, as well as sixfold higher youth suicide rates, poses a mounting challenge for minority, Indigenous, refugee, colonized, and immigrant communities. In environments where intergenerational transmission is often disrupted, artificial intelligence neural machine translation systems have…

  • Say It Right: AI Neural Machine Translation Empowers New Speakers To Revitalize Lemko (2022)

    Say It Right: AI Neural Machine Translation Empowers New Speakers To Revitalize Lemko (2022)

    15–22 minutes

    Abstract Artificial-intelligence powered neural machine translation might soon resuscitate endangered languages by empowering new speakers to communicate in real time using sentences quantifiably closer to the literary norm than those of native speakers, and starting from day one of their language reclamation journey. While Silicon Valley has been investing enormous resources into neural translation technology…

  • Yes I Speak… AI Neural Machine Translation in Multi-Lingual Training (2021)

    28–42 minutes

    ✅ This version of the contribution has been accepted for publication after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at this link. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use.…

Letters from Petro Orynycz

Get occasional notes from me on AI, languages, projects, cities, and life on the move.

I'll send a confirmation first. Letters count opens and clicks. Unsubscribe any time. Privacy policy