Description: Discover Lilt's research in Contextual AI and localization. Read research on large language models and on the future of global experiences.
professional (10533) modern (7127) cat (3799) easy (2884) translation (2398) api (2175) fast (2010) machine (1530) memory (829) machine translation (64)
205A3FD3-2C85-4B22-9382-BF91AE55C6B7 205A3FD3-2C85-4B22-9382-BF91AE55C6B7 How it Works Working with Lilt Global Experience Design Our Translators Quality Framework Technology Contextual AI Engine Platform Overview AI DataStudio Connectors API Security Solutions Services By Team By Industry By use case Translation Services Transcreation Services Review and Design Services Multimedia Services Global Brand Management Global Journey Mapping Insights and Analysis Data Labeling Localization Marketing Public Secto
Research Compact personalized models for neural machine translation. WUEBKER, SIMIANER, AND DENERO (EMNLP 2018) Research Hierarchical Incremental Adaptation for Statistical Machine Translation. WUEBKER, GREEN, AND DENERO (EMNLP 2015) Contextual AI Contextual AI Contextual AI for enterprise translation doesn’t just enable the translation of full sentences in isolation; it must make suggestions with deep business and content context — predicting what translators will type next, how they will transfer formatti
Research Automatic Bilingual Markup Transfer ZENKEL, WUEBKER, AND DENERO (ACL 2021) Research End-to-End Neural Word Alignment Outperforms GIZA++ ZENKEL, WUEBKER, AND DENERO (ACL 2020) Research Adding Interpretable Attention to Neural Translation Models Improves Word Alignment. ZENKEL, WUEBKER, AND DENERO (ARXIV 2019) Research Models and Inference for Prefix-Constrained Machine Translation. WUEBKER, GREEN, DENERO, HASAN, & LUONG (ACL 2016) Human-Computer Interaction and Data Science for Localization Human-Co