Whole-sentence exponential language models: a vehicle for linguistic-statistical integration

@article{Rosenfeld2001WholesentenceEL,
  title={Whole-sentence exponential language models: a vehicle for linguistic-statistical integration},
  author={Ronald Rosenfeld and Stanley F. Chen and Xiaojin Zhu},
  journal={Computer Speech & Language},
  year={2001},
  volume={15},
  pages={55-73}
}
Weintroduceanexponentiallanguagemodelwhichmodelsawholesentenceor utteranceasasingleunit. By avoiding thechainrule, themodeltreatseachsentenceasa “bag of features”,wherefeaturesarearbitrarycomputablepropertiesof the sentence.The new model is computationally moreefficient,andmorenaturallysuitedto modelingglobal sentential phenomena, thantheconditionalexponential(e.g. Maximum Entropy) modelsproposedto date. Using the modelis straightforward.Trainingthemodelrequiressampling from an… CONTINUE READING
Highly Influential
This paper has highly influenced a number of papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 105 citations. REVIEW CITATIONS

3 Figures & Tables

Topics

Statistics

051015'02'04'06'08'10'12'14'16'18
Citations per Year

106 Citations

Semantic Scholar estimates that this publication has 106 citations based on the available data.

See our FAQ for additional information.