Integrated Annotation for Biomedical Information Extraction, HLT/NAACL 2004 Workshop: Biolink 2004, pp. The final performance on the evaluation set is as follows. The featuers and parameters were tuned using the training data. The named entity tagger is trained on the NLPBA data set. Performance, see (the latest version usesĪnd gives slightly better performance than reported in the paper). Trained with different sets of documents. The table below shows the tagging accuracies of a tagger So the tagger works well on various types of biomedical documents. The GENIA tagger is trained not only on the Wall Street Journal corpusīut also on the GENIA corpus and the PennBioIE corpus , Which are often used as the training data for a general-purpose tagger. General-purpose part-of-speech taggers do not usually perform well onīiomedical text because lexical characteristics of biomedical documentsĪre considerably different from those of newspaper articles, You can also find a protein name with the named entity tags. You can easily extract four noun phrases ("Inhibition", "NF-kappaB activation", "the anti-apoptotic effect", and "isochamaejasmin") from this output by looking at the chunk tags. Isochamaejasmin isochamaejasmin NN B-NP O > echo "Inhibition of NF-kappaB activation reversed the anti-apoptotic effect of isochamaejasmin." |. The tagger outputs the base forms, part-of-speech (POS) tags, chunk tags, and named entity (NE) tags in the following tab-separated format.Ĭhunks are represented in the IOB2 format (B for BEGIN, I for INSIDE, and O for OUTSIDE). Prepare a text file containing one sentence per line, then
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |