Chemical entities are ubiquitous through the biomedical literature and the development of text-mining systems that can efficiently\r\nidentify those entities are required. Due to the lack of available corpora and data resources, the community has focused its efforts\r\nin the development of gene and protein named entity recognition systems, but with the release of ChEBI and the availability of an\r\nannotated corpus, this task can be addressed.We developed a machine-learning-based method for chemical entity recognition and\r\na lexical-similarity-based method for chemical entity resolution and compared them with Whatizit, a popular-dictionary-based\r\nmethod. Our methods outperformed the dictionary-based method in all tasks, yielding an improvement in F-measure of 20% for\r\nthe entity recognition task, 2ââ?¬â??5% for the entity-resolution task, and 15% for combined entity recognition and resolution tasks.
Loading....