Whole-sentence exponential language models: a vehicle for linguisticstatistical integration Export

@misc{citeulike:1218886, abstract = {We introduce an exponential language model which models a whole sentence or utterance as a single unit. By avoiding the chain rule, the model treats each sentence as a \"bag of features\", where features are arbitrary computable properties of the sentence. The new model is computationally more efficient, and more naturally suited to modeling global sentential phenomena, than the conditional exponential (e.g. Maximum Entropy) models proposed to date. Using the model is straightforward. Training...}, author = {Rosenfeld, R. and Chen, S. and Zhu, X.}, citeulike-article-id = {1218886}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.2631}, keywords = {discriminative, lm, log-linear}, posted-at = {2007-10-17 14:00:33}, priority = {2}, title = {Whole-sentence exponential language models: a vehicle for linguisticstatistical integration}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.2631}, year = {2001} }

TY - GEN ID - citeulike:1218886 L3 - citeulike-article-id:1218886 N2 - We introduce an exponential language model which models a whole sentence or utterance as a single unit. By avoiding the chain rule, the model treats each sentence as a "bag of features", where features are arbitrary computable properties of the sentence. The new model is computationally more efficient, and more naturally suited to modeling global sentential phenomena, than the conditional exponential (e.g. Maximum Entropy) models proposed to date. Using the model is straightforward. Training... TI - Whole-sentence exponential language models: a vehicle for linguisticstatistical integration KW - discriminative KW - lm KW - log-linear AU - Rosenfeld, R AU - Chen, S AU - Zhu, X PY - 2001/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.2631 ER -