A whole sentence maximum entropy language model Export

@misc{citeulike:1774926, abstract = {We introduce a new kind of language model, which models whole sentences or utterances directly using the Maximum Entropy paradigm. The new model is conceptually simpler, and more naturally suited to modeling whole-sentence phenomena, than the conditional ME models proposed to date. By avoiding the chain rule, the model treats each sentence or utterance as a \"bag of features\", where features are arbitrary computable properties of the sentence. The model is unnormalizable, but this does not...}, author = {Rosenfeld, R.}, citeulike-article-id = {1774926}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.4834}, keywords = {contrastive, discriminative, lm, log-linear, maxent}, posted-at = {2007-10-16 16:04:11}, priority = {2}, title = {A whole sentence maximum entropy language model}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.4834}, year = {1997} }

TY - GEN ID - citeulike:1774926 L3 - citeulike-article-id:1774926 N2 - We introduce a new kind of language model, which models whole sentences or utterances directly using the Maximum Entropy paradigm. The new model is conceptually simpler, and more naturally suited to modeling whole-sentence phenomena, than the conditional ME models proposed to date. By avoiding the chain rule, the model treats each sentence or utterance as a "bag of features", where features are arbitrary computable properties of the sentence. The model is unnormalizable, but this does not... TI - A whole sentence maximum entropy language model KW - contrastive KW - discriminative KW - lm KW - log-linear KW - maxent AU - Rosenfeld, R PY - 1997/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.4834 ER -