Samuel Larkin
  • Bio
  • Papers
  • Talks
  • News
  • Experience
  • Projects
  • Recent & Upcoming Talks
    • Example Talk
    • Trixie: Be a Good Cluster-Citizen
  • Publications
    • MSLC25: Metric Performance on Low-Quality Machine Translation, Empty Strings, and Language Variants
    • NRC Systems for the WMT2025-LRSL Shared Task
    • Challenges in Technical Regulatory Text Variation Detection
    • Speech Generation for Indigenous Language Education
    • MSLC24 Submissions to the General Machine Translation Task
    • MSLC24: Further Challenges for Metrics on a Wide Landscape of Translation Quality
    • Some Tradeoffs in Continual Learning for Parliamentary Neural Machine Translation Systems
    • Speech Generation for Indigenous Language Education
    • Metric Score Landscape Challenge (MSLC23): Understanding Metrics′ Performance on a Wider Landscape of Translation Quality
    • Long to reign over us: A Case Study of Machine Translation and a New Monarch
    • Terminology in Neural Machine Translation: A Case Study of the Canadian Hansard
    • NRC-CNRC Systems for Upper Sorbian-German and Lower Sorbian-German Machine Translation 2021
    • Like Chalk and Cheese? On the Effects of Translationese in MT Training
    • NRC-CNRC Machine Translation Systems for the 2021 AmericasNLP Shared Task
    • Machine Translation Reference-less Evaluation using YiSi-2 with Bilingual Mappings of Massive Multilingual Language Model
    • NRC Systems for Low Resource German-Upper Sorbian Machine Translation 2020: Transfer Learning with Lexical Modifications
    • NRC Systems for the 2020 Inuktitut-English News Translation Task
    • The Nunavut Hansard Inuktitut--English Parallel Corpus 3.0 with Preliminary Machine Translation Results
    • Bursty event detection on social media
    • Multi-Source Transformer for Kazakh-Russian-English Neural Machine Translation
    • An example preprint / working paper
    • Accurate semantic textual similarity for cleaning noisy parallel corpora using semantic machine translation evaluation metric: The NRC supervised submissions to the Parallel Corpus Filtering task
    • Measuring sentence parallelism using Mahalanobis distances: The NRC unsupervised submissions to the WMT18 Parallel Corpus Filtering shared task
    • EuroGames16: Evaluating Change Detection in Online Conversation
    • NRC Machine Translation System for WMT 2017
    • Cost Weighting for Neural Machine Translation Domain Adaptation
    • An example journal article
    • Transferring markup tags in statistical machine translation: a two-stream approach
    • An example conference paper
    • PORT: a Precision-Order-Recall MT Evaluation Metric for Tuning
    • Lessons from NRC′s Portage System at WMT 2010
    • Incorporating Knowledge of Source Language Text in a System for Dictation of Document Translations
    • PortageLive: delivering machine translation technology via virtualization
    • Tightly Packed Tries: How to Fit Large Models into Memory, and Make them Load Fast, Too
    • PORTAGE in the NIST 2009 MT Evaluation
    • NRC`s PORTAGE System for WMT 2007
    • Manageable Phrase-based Statistical Machine Translation Models–with Pseudo-code and Proofs
    • PORTAGE: with Smoothed Phrase Tables and Segment Choice Models
    • PORTAGE Phrase-Based System for Chinese-to-English Translation
  • Projects
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • Projects
    • EveryVoice
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python

Tightly Packed Tries: How to Fit Large Models into Memory, and Make them Load Fast, Too

Jun 1, 2009·
Ulrich Germann
,
Eric Joanis
,
Samuel Larkin
· 0 min read
Cite URL
Last updated on Jun 1, 2009
← PortageLive: delivering machine translation technology via virtualization Aug 1, 2009
PORTAGE in the NIST 2009 MT Evaluation Jan 1, 2009 →

© 2026 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.