php - NLP creating a model out of POS tags -
i trying create knowledgebase based on text mining. using genia corpus tag words parts of speech. given 2 terms text, how create model finds out relation?
eg text:
hif1a gene involved in hypoxic regulation. hypoxia regulates brca1 gene expression associated in breast cancer.
i have pos tagged out.
word base form part-of-speech hif1a hif1a nn gene gene nn vbz involved involve vbn in in in hypoxic hypoxic jj regulation regulation nn . . . hypoxia hypoxia nn rb regulates regulate vbz brca1 brca1 nn gene gene nn wdt vbz rb associated associate vbn in in in breast breast nn cancer cancer nn
i writing web interface when queried brca1 , hypoxia should tell there positive regulation between them. when queried hif1a , hypoxia should tell there positive regulation based on these sentences.
now have pos tagged dont know how proceed in creating model come identifying relation between them. example. want general biomedical terms , texts.
anyone suggestions?
relying solely on output of pos tagger you'll have define local grammar rules (patterns).
personally, suggest use (syntactic) parser argument structures regulate(hypoxia,brca1)
...
Comments
Post a Comment