Nahm, Un-Yong and Raymond Mooney. 2000. A mutually beneficial integration of data mining and information extraction. In The 17th National Conference on Artificial Intelligence (AAAI-2000), pages 627--632.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....in a probabilistic framework, our algorithm leverages numerous sources of weak evidence to obtain a globally optimal set of predictions. We conjecture that this idea could be extended to other tasks, such as information extraction (using retrieved data to bias the retrieval of additional data; see [13]) or personalization (recommending multiple items simultaneously ) One important direction of future work concerns the hierarchical structure of the domain and datatype taxonomies. We have explored using such structure in our evaluation, but it may be useful to integrate these hierarchies into ....

U. Nahm and R. Mooney. A mutually beneficial integration of data mining and information extraction. In Proc. 17th Nat. Conf. Artificial Intelligence, pages 627-- 632, 2000.

....the inevitable difficulties. Much noise and error remains in these soft joins, and this approach could not support complex relational data mining. Some of the most truly integrated work in extraction and data mining has been done by Ray Mooney s group at UT Austin. For example, in one project [Nahm and Mooney, 2000] , twelve fields of data are extracted from USENET computer related job ads using a rule learner. The fields include programming language, hardware platform, application area, etc. A second rule learner is applied to an imperfectly extracted database to produce rules that will predict the value in ....

Un Yong Nahm and Raymond J. Mooney. A mutually beneficial integration of data mining and information extraction. In AAAI/IAAI, pages 627--632, 2000.

....a probabilistic framework, our algorithm leverages numerous sources of weak evidence to obtain a globally optimal set of predictions. We conjecture that this idea could be extended to other tasks, such as information extraction (using retrieved data to to bias the retrieval of additional data; see [Nahm and Mooney, 2000]) or personalization (recommending multiple items simultaneously ) One important direction of future work concerns the hierarchical structure of the domain and datatype taxonomies. We have explored using such structure in our evaluation, but it may be useful to integrate these hierarchies into ....

U. Nahm and R. Mooney. A mutually beneficial integration of data mining and information extraction. In Proc. 17th Nat. Conf. Artificial Intelligence, pages 627--632, 2000.

....Rapier [Califf and Mooney, 1999] The next selected document is the one on which the learned rule sets most disagree. Bag Invoke the learning algorithm on different partitions of the available training data. As with Committee, the document that maximizes disagreement is selected. Mine Following [Nahm and Mooney, 2000] , learn a set of extraction rules, and then mine a set of association rules for predicting which extracted items frequently cooccur. Select for annotation the document whose extracted content most contradicts the association rules. Each algorithm encodes different heuristics for identifying ....

U. Nahm and R. Mooney. A mutually beneficial integration of data mining and information extraction. In Proc. 17th Nat. Conf. Artifical Intelligence, 2000.

No context found.

Nahm, Un-Yong and Raymond Mooney. 2000. A mutually beneficial integration of data mining and information extraction. In The 17th National Conference on Artificial Intelligence (AAAI-2000), pages 627--632.

....2 consequent words, the word storage co occurs within 3 words. is an episode rule discovered from a collection of Finnish legal documents. In addition, decision tree methods such as C4.5 and C5.0, and rule learners such as FOIL, and RIPPER have been used to discover patterns from textual data [Nahm and Mooney, 2000b; Ghani et al. 2000] All of these existing methods discover rules requiring an exact match. 2.2 Mining Information Extracted from Text Nahm and Mooney(2000a; 2000b) introduced an alternative framework for text mining based on the integration of information extraction (IE) and traditional ....

....tree methods such as C4.5 and C5.0, and rule learners such as FOIL, and RIPPER have been used to discover patterns from textual data [Nahm and Mooney, 2000b; Ghani et al. 2000] All of these existing methods discover rules requiring an exact match. 2. 2 Mining Information Extracted from Text Nahm and Mooney(2000a; 2000b) introduced an alternative framework for text mining based on the integration of information extraction (IE) and traditional data mining. IE is a form of shallow text understanding that locates specific pieces of data in natural language text. Traditional data mining assumes that information is ....

Un Yong Nahm and Raymond J. Mooney. A mutually beneficial integration of data mining and information extraction. In Proceedings of the Seventeenth National Conference on Artificial Intelligence, pages 627--632, Austin, TX, July 2000.

No context found.

Un-Yong Nahm and Raymond Mooney. A mutually beneficial integration of data mining and information extraction. In Proceedings of AAAI-2000, pages 627--632, 2000.

No context found.

U. Y. Nahm and R. J. Mooney. A mutually beneficial integration of data mining and information extraction. In Proc. 17th AAAI, pages 627--632, 2000.

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