Abstract: Studies on MetaMap and MaxMatcher has shown that both concept extraction systems suffer from overgeneration problems. Over-generation occurs when the extraction systems mistakenly select an irrelevant concept. One of the reasons for these errors is that these systems use the words to weight the terms of the concepts. In this paper, an Integer Linear Programming model is used to select the optimal subset of extracted concept mentions covering the largest number of important words in the document to be indexed. Then each concept mentions that this set is mapped to a unique concept in UMLS using an information retrieval model.

Samassi Adama, Brou Konan Marcellin, Gooré Bi Tra and Prosper Kimou, “Efficient Reduction of Overgeneration Errors for Automatic Controlled Indexing with an Application to the Biomedical Domain” International Journal of Advanced Computer Science and Applications(IJACSA), 9(12), 2018. http://dx.doi.org/10.14569/IJACSA.2018.091225

@article{Adama2018,
title = {Efficient Reduction of Overgeneration Errors for Automatic Controlled Indexing with an Application to the Biomedical Domain},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2018.091225},
url = {http://dx.doi.org/10.14569/IJACSA.2018.091225},
year = {2018},
publisher = {The Science and Information Organization},
volume = {9},
number = {12},
author = {Samassi Adama and Brou Konan Marcellin and Gooré Bi Tra and Prosper Kimou}
}