Class-based n-gram models of natural language

@article{176316, abstract = {We address the problem of predicting a word from previous words in a sample of text. In particular, we discuss n-gram models based on classes of words. We also discuss several statistical algorithms for assigning words to classes based on the frequency of their co-occurrence with other words. We find that we are able to extract classes that have the flavor of either syntactically based groupings or semantically based groupings, depending on the nature of the underlying statistics.}, address = {Cambridge, MA, USA}, author = {Brown, Peter F. and Desouza, Peter V. and Mercer, Robert L. and Della Pietra, Vincent J. and Lai, Jenifer C. }, citeulike-article-id = {918606}, journal = {Comput. Linguist.}, keywords = {clustering, n-gram, nlp}, local-url = {file://localhost/Users/khofmann/Papers/QA/p467-brown.pdf}, number = {4}, pages = {467--479}, posted-at = {2006-10-30 16:12:09}, priority = {0}, publisher = {MIT Press}, title = {Class-based n-gram models of natural language}, volume = {18}, year = {1992} }

TY - JOUR ID - 176316 L3 - citeulike-article-id:918606 N2 - We address the problem of predicting a word from previous words in a sample of text. In particular, we discuss n-gram models based on classes of words. We also discuss several statistical algorithms for assigning words to classes based on the frequency of their co-occurrence with other words. We find that we are able to extract classes that have the flavor of either syntactically based groupings or semantically based groupings, depending on the nature of the underlying statistics. IS - 4 JF - Comput. Linguist. AD - Cambridge, MA, USA EP - 479 TI - Class-based n-gram models of natural language PB - MIT Press VL - 18 SP - 467 KW - clustering KW - n-gram KW - nlp AU - Brown, Peter AU - Desouza, Peter AU - Mercer, Robert AU - Della Pietra, Vincent AU - Lai, Jenifer PY - 1992/// ER -