Tractable Learning and Inference with Higher-Order Representations. Culotta, A. & McCallum, A. In ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS), 2006.
Paper bibtex @inproceedings{DBLP:conf/icml_ws/Culotta06,
author = {Aron Culotta and Andrew McCallum},
title = {Tractable Learning and Inference with Higher-Order Representations},
booktitle = {ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS)},
year = {2006},
url = {https://people.cs.umass.edu/~mccallum/papers/tractable-icmlws06.pdf},
sum = {When working with CRFs having features based on first-order logic, the "unrolled" graphical model would be far to large to fully instantiate. This paper describes a method leveraging MCMC to perform inference and learning while only partially instantiating the model. Positive results on entity resolution (of research papr authors) are described.},
}
Downloads: 0
{"_id":"mo2P9YHx4djLvW3jy","bibbaseid":"culotta-mccallum-tractablelearningandinferencewithhigherorderrepresentations-2006","downloads":0,"creationDate":"2018-12-17T19:54:49.705Z","title":"Tractable Learning and Inference with Higher-Order Representations","author_short":["Culotta, A.","McCallum, A."],"year":2006,"bibtype":"inproceedings","biburl":"http://www.iesl.cs.umass.edu/bibtex_paper_list/iesl_publication.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Aron"],"propositions":[],"lastnames":["Culotta"],"suffixes":[]},{"firstnames":["Andrew"],"propositions":[],"lastnames":["McCallum"],"suffixes":[]}],"title":"Tractable Learning and Inference with Higher-Order Representations","booktitle":"ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS)","year":"2006","url":"https://people.cs.umass.edu/~mccallum/papers/tractable-icmlws06.pdf","sum":"When working with CRFs having features based on first-order logic, the \"unrolled\" graphical model would be far to large to fully instantiate. This paper describes a method leveraging MCMC to perform inference and learning while only partially instantiating the model. Positive results on entity resolution (of research papr authors) are described.","bibtex":"@inproceedings{DBLP:conf/icml_ws/Culotta06,\n author = {Aron Culotta and Andrew McCallum},\n title = {Tractable Learning and Inference with Higher-Order Representations},\n booktitle = {ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS)},\n year = {2006},\n url = {https://people.cs.umass.edu/~mccallum/papers/tractable-icmlws06.pdf},\n sum = {When working with CRFs having features based on first-order logic, the \"unrolled\" graphical model would be far to large to fully instantiate. This paper describes a method leveraging MCMC to perform inference and learning while only partially instantiating the model. Positive results on entity resolution (of research papr authors) are described.},\n}\n\n","author_short":["Culotta, A.","McCallum, A."],"key":"DBLP:conf/icml_ws/Culotta06","id":"DBLP:conf/icml_ws/Culotta06","bibbaseid":"culotta-mccallum-tractablelearningandinferencewithhigherorderrepresentations-2006","role":"author","urls":{"Paper":"https://people.cs.umass.edu/~mccallum/papers/tractable-icmlws06.pdf"},"downloads":0,"html":""},"search_terms":["tractable","learning","inference","higher","order","representations","culotta","mccallum"],"keywords":[],"authorIDs":["5c17ff093f5a2e1000000237"],"dataSources":["AzT84AFaHQ6JExJ8R"]}