Discover Lilt's research in machine translation and localization

The Lilt research team is working on driving the future of translation technology.
D8B2BF20-55AB-407B-A8A8-0A10AFFA0F9D
Online Adaptation of Neural Machine Translation Models
Online Adaptation of Neural Machine Translation Models
Lilt's translation models adapt to translators as they work, updating parameters automatically with each sentence translated. This tight loop allows adaptation to specific document-level and project-level vocabulary, structural patterns, and idiosyncrasies. Our research team focuses on fast and effective adaptation of state-of-the-art neural machine translation models using methods that are efficient enough to support large-scale personalized neural machine translation.

Related Research

Interactive Neural Machine Translation
Interactive Neural Machine Translation
An interactive neural machine translation system that supports localization must do more than translate full sentences in isolation: it must make suggestions about what translators will type next in context, how they will transfer formatting from the source document to the target, and what edits will be performed by reviewers. Interactive systems must take termbases, translation memories, and contextual constraints into account for all of these suggestions. Our research team focuses on the full range of automatically generated suggestions that can improve the speed and quality of human localization work across translation, reviewing, and quality assurance.

Related Research

Human-Computer Interaction and Data Science for Localization
Human-Computer Interaction and Data Science for Localization
Lilt's human-in-the-loop approach to localization places both professional translators and artificial intelligence technology together at the core of our operations. A broad range of human-computer interaction problems arise in this setting, from text-editing interfaces to assigning translators to project workflows. Our research team focuses on interaction design across the Lilt platform and data science across Lilt's business and translator community.

Related Research

Meet the Lilt Research Team

John DeNero
John DeNero
Co-Founder and Chief Scientist
Spence Green
Spence Green
Co-founder and CEO
Joern Wuebker
Joern Wuebker
Director of Research
Patrick Simianer
Patrick Simianer
Principal Research Scientist
Geza Kovacs
Geza Kovacs
Senior Research Scientist
Sai Gouravajhala
Sai Gouravajhala
Senior Research Scientist
Hannah Yan
Hannah Yan
Senior Data Scientist
Thomas Zenkel
Thomas Zenkel
Research Scientist
Gabriel Bretschner
Gabriel Bretschner
Research Scientist
Aditya Shastry
Aditya Shastry
Research Scientist
Jessy Lin
Jessy Lin
Research Scientist
Ze'ev Shamir
Ze'ev Shamir
Senior Software Engineer, Research
Yunsu Kim
Yunsu Kim
Research Scientist
Jakob Uszkoreit
Inceptive technology that understands all people and culture
"So many interesting translation problems touch on cultural issues and contextual clues. If we really want to reach what we would consider the highest possible level of quality achievable, we have to build technology that better understands all people and cultures."
Jakob Uszkoreit
Co-founder at Inceptive

Translate with Lilt today