T
Thorsten Brants
Researcher at Google
Publications - 21
Citations - 1279
Thorsten Brants is an academic researcher from Google. The author has contributed to research in topics: Language model & Machine translation. The author has an hindex of 11, co-authored 21 publications receiving 1231 citations.
Papers
More filters
Proceedings Article
Large Language Models in Machine Translation
TL;DR: Systems, methods, and computer program products for machine translation are provided for backoff score determination as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.
Patent
Encoding and adaptive, scalable accessing of distributed models
Franz Josef Och,Jeffrey Dean,Thorsten Brants,Alexander Franz,Jay Ponte,Peng Xu,Sha-Mayn Teh,Jeffrey Chin,Ignacio Thayer,Anton Carver,Daniel Rosart,John S. Hawkins,Karel Driesen +12 more
TL;DR: In this article, the authors present systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.
Proceedings Article
Distributed Word Clustering for Large Scale Class-Based Language Modeling in Machine Translation
Jakob Uszkoreit,Thorsten Brants +1 more
TL;DR: This paper introduces a modification of the exchange clustering algorithm with improved eciency for certain partially class-based models and a distributed version of this algorithm to eciently obtain automatic word classifications for large vocabularies using such large training corpora.
Proceedings ArticleDOI
A Context Pattern Induction Method for Named Entity Extraction
TL;DR: A novel context pattern induction method is presented for information extraction, specifically named entity extraction, that extended several classes of seed entity lists into much larger high-precision lists and improved the accuracy of a conditional random field-based named entity tagger.
Patent
Machine translation using information retrieval
Hayden Shaw,Thorsten Brants +1 more
TL;DR: In this article, the authors provide a method for machine translation using information retrieval techniques, which includes providing a received input segment as a query to a search engine, the search engine searching an index of one or more collections of documents, receiving one of the candidate segments in response to the query, determining a similarity of each candidate segment to the received input segments, and for one of candidate segments having a determined similarity that exceeds a threshold similarity, providing a translated target segment corresponding to the respective candidate segment.