IEEE/ACM Transactions on Audio Speech and Language Processing · 2016 · 14 citations · 33 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingLanguage ModelingLanguage ModelsN-gram AnalysisSpeech RecognitionExponential InterpolationLexical PredictionMaximum Entropy ModelingPart-of-speech Features
This paper proposes an exponential interpolation to merge a part-of-speech-based language model and a word-based <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$n$</tex-math></inline-formula> -gram language model to accomplish word prediction tasks. In order to find a set of mathematical equations to properly describe the language modeling, a model based on partial differential equations is proposed. With the appropriate initial conditions, it was found an interpolation model similar to the traditional maximum entropy language model. Improvements in keystroke saved and perplexity over the word-based <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$n$</tex-math></inline-formula> -gram language model and two other traditional interpolation models is obtained, considering three different languages. The proposed interpolation model also provides additional improvement in hit rate parameter.
33
An introduction to ROC analysis
Tom Fawcett · Pattern Recognition Letters · 2005 · 21.3K citations
Recurrent neural network based language model
Tomáš Mikolov, Martin Karafiát, Lukáš Burget et al. · 2010 · 5.4K citations