Unsupervised learning of natural languages Export

@article{citeulike:312476, abstract = {10.1073/pnas.0409746102 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 (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.}, address = {School of Physics and Astronomy and School of Computer Science, Tel Aviv University, Tel Aviv 69978, Israel.}, author = {Solan, Z. and Horn, D. and Ruppin, E. and Edelman, S.}, citeulike-article-id = {312476}, citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.0409746102}, citeulike-linkout-1 = {http://www.pnas.org/content/102/33/11629.abstract}, citeulike-linkout-2 = {http://www.pnas.org/content/102/33/11629.full.pdf}, citeulike-linkout-3 = {http://www.pnas.org/cgi/content/abstract/102/33/11629}, citeulike-linkout-4 = {http://www.isrl.uiuc.edu/~amag/langev/paper/solan05languageLearningPNAS.html}, citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/16087885}, citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=16087885}, citeulike-linkout-7 = {http://www.pnas.org/cgi/content/abstract/102/33/11629}, day = {16}, doi = {10.1073/pnas.0409746102}, issn = {0027-8424}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, keywords = {3i, 3r, algorithm-adios, grammar, grammar-context-free, language-acquisition, learning-unsupervised, motif-extraction, rule, search-path}, month = {August}, number = {33}, pages = {11629--11634}, posted-at = {2006-07-09 06:45:25}, priority = {0}, title = {Unsupervised learning of natural languages}, url = {http://dx.doi.org/10.1073/pnas.0409746102}, volume = {102}, year = {2005} }

TY - JOUR ID - citeulike:312476 L3 - citeulike-article-id:312476 N2 - 10.1073/pnas.0409746102 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 (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 of the United States of America SN - 0027-8424 AD - School of Physics and Astronomy and School of Computer Science, Tel Aviv University, Tel Aviv 69978, Israel. EP - 11634 TI - Unsupervised learning of natural languages VL - 102 SP - 11629 KW - 3i KW - 3r KW - algorithm-adios KW - grammar KW - grammar-context-free KW - language-acquisition KW - learning-unsupervised KW - motif-extraction KW - rule KW - search-path AU - Solan, Z AU - Horn, D AU - Ruppin, E AU - Edelman, S PY - 2005/08/16/ UR - http://dx.doi.org/10.1073/pnas.0409746102 ER -