| A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL99 - Workshop for Unsupervised Learning in Natural Language Processing, 1999. |
....surrounding the occurrence of the investigated relation. In comparison, we aim at finding less structured information, for which such simple patterns wouldn t be sufficient. Finally, the use of bootstrapping and other statistical methods for information extraction has also been presented e.g. in [7] and [9] The class specific indicators will apparently be more complex than the current ones. 7 FUTURE WORK Given the three topics of the paper, actual results (based on Open Directory data) have been so far obtained only for indicator learning and ontological analysis. The most challenging ....
A. McCallum, K. Nigam, Text Classification by Bootstrapping with Keywords, EM and Shrinkage. In ACL'99 Workshop for Unsupervised Learning in NLP, 1999.
....determined in the future. 4 Related Work The common approach to overcome the lack of classified training examples in text categorisation is to apply statistical techniques consisting in iterative automated labelling of unclassified examples based on a few classified ones (bootstrapping, see [1] [4], 5] So far, we have not considered such techniques, and instead rely on the prior work of a human indexer of the web directory. While directories have already been used for learning to classify whole documents [3] their use for information extraction seems to be rather innovative. Our work ....
Andrew McCallum and Kamal Nigam. Text Classification by Bootstrapping with Keywords, EM and Shrinkage. In ACL'99 Workshop for Unsupervised Learning in NLP, 1999.
....computer science papers in postscript format [16] turns the postscript into plain text, uses hidden Markov models to extract the paper titles, authors, institutions, references, etc. 20] and uses statistical text classification to categorize the papers into a 70 leaf Yahoo like topic hierarchy [13]. For example, one branch from top to bottom is: Artificial Intelligence, Machine Learning, Reinforcement Learning. References in papers are automatically matched to each other and to papers using a soft matching criteria that can detect when two references are referring to the same paper, even ....
....by realigning the principal eigenvector to raise the authority of a small number of theory papers, we would see the authority of many other theory papers would rise. We realize that, if our goal was merely the classification of papers into subtopics, there are much better ways to accomplish this [13]. Instead, we are using subtopics as an objective indicator that we expect to be correlated with a user s interests. Beginning with a root set of all documents in the Machine Learning topic, we ran 10 iterations of HITS to establish initial authority rankings. We selected a small number of ....
A. McCallum, K. Nigam, Text Classification by Bootstrapping with Keywords, EM and Shrinkage, ACL Workshop for Unsupervised Learning in Natural Language Processing, 1999
No context found.
A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL99 - Workshop for Unsupervised Learning in Natural Language Processing, 1999.
No context found.
A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL99 - Workshop for Unsupervised Learning in Natural Language Processing, 1999.
No context found.
A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL Workshop for Unsupervised Learning in Natural Language Processing, 1999.
No context found.
Andrew McCallum and Kamal Nigam. Text Classification by Bootstrapping with Keywords, EM and Shrinkage. In ACL '99 Workshop for Unsupervised Learning in Natural Language Processing, pp. 52-58, 1999.
No context found.
A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL99 - Workshop for Unsupervised Learning in Natural Language Processing, 1999.
No context found.
A. McCallum and K. Nigam. Text classification by bootstrapping with keywords. In ACL99 - Workshop for Unsupervised Learning in Natural Language Processing, 1999.
No context found.
Andrew McCallum and Kamal Nigam. Text Classification by Bootstrapping with Keywords, EM and Shrinkage. In ACL'99 Workshopfor Unsupervised Learning in N , 1999.
No context found.
McCallum, A., Nigam, K., (1999) Text Classification by Bootstrapping with Keywords, EM and Shrinkage. Technical Report, Just Research http://www.cs.cmu.edu/~mccallum.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC