Empirical Studies in Learning to Read. Freedman, M., Loper, E., Boschee, E., & Weischedel, R. In Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading, of FAM-LbR '10, pages 61–69, USA, 2010. Association for Computational Linguistics.
abstract   bibtex   
In this paper, we present empirical results on the challenge of learning to read. That is, given a handful of examples of the concepts and relations in an ontology and a large corpus, the system should learn to map from text to the concepts/relations of the ontology. In this paper, we report contrastive experiments on the recall, precision, and F-measure (F) of the mapping in the following conditions: (1) employing word-based patterns, employing semantic structure, and combining the two; and (2) fully automatic learning versus allowing minimal questions of a human informant.
@inproceedings{10.5555/1866775.1866783,
author = {Freedman, Marjorie and Loper, Edward and Boschee, Elizabeth and Weischedel, Ralph},
title = {Empirical Studies in Learning to Read},
year = {2010},
publisher = {Association for Computational Linguistics},
address = {USA},
abstract = {In this paper, we present empirical results on the challenge of learning to read. That is, given a handful of examples of the concepts and relations in an ontology and a large corpus, the system should learn to map from text to the concepts/relations of the ontology. In this paper, we report contrastive experiments on the recall, precision, and F-measure (F) of the mapping in the following conditions: (1) employing word-based patterns, employing semantic structure, and combining the two; and (2) fully automatic learning versus allowing minimal questions of a human informant.},
booktitle = {Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading},
pages = {61–69},
numpages = {9},
location = {Los Angeles, California},
series = {FAM-LbR '10}
}

Downloads: 0