Skip to search formSkip to main content
You are currently offline. Some features of the site may not work correctly.

Katz's back-off model

Known as: Backoff weight 
Katz back-off is a generative n-gram language model that estimates the conditional probability of a word given its history in the n-gram. It… Expand
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2017
2017
Categorical models are a natural fit for many problems. When learning the distribution of categories from samples, high… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
2013
2013
The goal of this research is to design a multi-label classification model which determines the research topics of a given… Expand
  • figure 1
  • table 2
  • figure 2
Highly Cited
2013
Highly Cited
2013
We present an affective text analysis model that can directly estimate and combine affective ratings of multi-word terms, with… Expand
  • table II
  • table III
  • figure 1
  • figure 2
  • figure 3
2012
2012
Although significant improvements have been achieved in statistical machine translation (SMT), even the best machine translation… Expand
  • table 1
  • table 2
  • table 3
2011
2011
Capturing users' future search actions has many potential applications such as query recommendation, web page re-ranking… Expand
  • figure 1
  • table II
  • table III
  • table IV
  • figure 2
2009
2009
In this paper we propose a back-off discriminative acoustic model for Automatic Speech Recognition (ASR). We use a set of broad… Expand
  • table 1
  • table 2
2001
2001
This work describes a method for generating back-off models for context-dependent unit modeling. The main characteristic of the… Expand
  • figure 1
  • figure 2
  • table 1
  • table 2
  • table 4
2000
2000
Though the statistical language modeling plays an important role in speech recognition, there are still many problems that are… Expand
  • table II
  • table 1
1997
1997
This paper presents a corpus-based method to assign grammatical subject/object relations to ambiguous German constructs. It makes… Expand
  • figure 1
1996
1996
  • J. Ueberla
  • IEEE Trans. Speech Audio Process.
  • 1996
  • Corpus ID: 16869337
An existing clustering algorithm is extended to deal with higher order N-grams and a faster heuristic version is developed. Even… Expand
  • table 1
  • table 2
  • table 3
  • table 4
  • table 5