Unsupervised learning of natural languages Export

@article{citeulike:310609, abstract = {We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The ADIOS (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics.}, author = {Solan, Zach and Horn, David and Ruppin, Eytan and Edelman, Shimon}, citeulike-article-id = {310609}, citeulike-linkout-0 = {http://www.pnas.org/cgi/content/abstract/102/33/11629}, comment = {Full text of paper available at http://www.cs.tau.ac.il/\~{}ruppin/pnas\_adios.pdf}, day = {16}, editor = {Mcclelland, James L.}, journal = {Proceedings of the National Academy of Sciences}, keywords = {algorithms, bioinformatics, linguistics}, month = {August}, number = {33}, pages = {11629--11634}, posted-at = {2005-09-01 19:02:29}, priority = {0}, title = {Unsupervised learning of natural languages}, url = {http://www.pnas.org/cgi/content/abstract/102/33/11629}, volume = {102}, year = {2005} }

TY - JOUR ID - citeulike:310609 L3 - citeulike-article-id:310609 N2 - We address the problem, fundamental to linguistics, bioinformatics, and certain other disciplines, of using corpora of raw symbolic sequential data to infer underlying rules that govern their production. Given a corpus of strings (such as text, transcribed speech, chromosome or protein sequence data, sheet music, etc.), our unsupervised algorithm recursively distills from it hierarchically structured patterns. The ADIOS (automatic distillation of structure) algorithm relies on a statistical method for pattern extraction and on structured generalization, two processes that have been implicated in language acquisition. It has been evaluated on artificial context-free grammars with thousands of rules, on natural languages as diverse as English and Chinese, and on protein data correlating sequence with function. This unsupervised algorithm is capable of learning complex syntax, generating grammatical novel sentences, and proving useful in other fields that call for structure discovery from raw data, such as bioinformatics. IS - 33 JF - Proceedings of the National Academy of Sciences EP - 11634 TI - Unsupervised learning of natural languages VL - 102 SP - 11629 KW - algorithms KW - bioinformatics KW - linguistics N1 - Full text of paper available at http://www.cs.tau.ac.il/~ruppin/pnas_adios.pdf AU - Solan, Zach AU - Horn, David AU - Ruppin, Eytan AU - Edelman, Shimon A2 - Mcclelland, James PY - 2005/08/16/ UR - http://www.pnas.org/cgi/content/abstract/102/33/11629 ER -