Randomised Language Modelling for Statistical Machine Translation

By David Talbot, Miles Osborne. 2007

84 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Machine Translation

Citations in the corpus

Data Portraits: Recording Foundation Model Training Data (2023, methodology): “Talbot and Osborne [34] use Bloom filters to construct language models while others used similar structures to count features [16, 36].”
11,001 New Features for Statistical Machine Translation (2009, methodology): “The language models are represented using randomized data structures similar to those of Talbot et al. (2007).”
Large and Diverse Language Models for Statistical Machine Translation (2008, methodology): “Also the use of lossy data structures based on Bloom ﬁlters has been demonstrated to be effective for LMs (Talbot and Osborne, 2007a; Talbot and Osborne, 2007b).”
Experiments in Morphosyntactic Processing for Translating to and from German (2009, background): “RANDLM (Talbot and Osborne, 2007) performs well and scaled to the full data with improvement (resulting in our best overall system).”
Exponential Reservoir Sampling for Streaming Language Models (2014, background): “Work by Talbot and Osborne (2007), Van Durme and Lall (2009) and Goyal et al. (2009) considered the problem of building very large language models via the use of randomized data structures known as sketches .”
Randomized Language Models via Perfect Hash Functions (2008, methodology): “Following (Talbot and Osborne, 2007a) we can avoid unnecessary false positives by not querying for the longer n -gram in such cases.”
Scalable Modified Kneser-Ney Language Model Estimation (2013, methodology): “Better compression methods (Guthrie and Hepple, 2010; Talbot and Osborne, 2007) and distributed language models (Brants et al., 2007) could reduce hardware requirements.”
Probabilistic Counting with Randomized Storage (2009, unknown): “, [Talbot and Osborne, 2007; Talbot and Brants, 2008]).”