1 / 5

Information Extraction Techniques from Biomedical Texts

This document outlines rules for extracting information from biomedical texts, highlighting the importance of the order of rules, where high-frequency appearances come first. It discusses various domains defined by verbs, such as studies related to drugs or therapeutic modalities. An example illustrates the extraction process, demonstrating how dependency parsing identifies subjects and objects in sentences. This framework aims to enhance the effectiveness of pattern matching in extracting meaningful data from complex biomedical literature.

ramya
Télécharger la présentation

Information Extraction Techniques from Biomedical Texts

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Information Extraction from biomedical texts Mohammed Alshayeb 11/16/2009

  2. Rules

  3. Order of Rules • High frequency appearance come first. • More evidences are needed.

  4. Domains • Domains have verbs. • e.g. studies/MM-DRUG_CHEMICAL_COMPOUND_THERAPEUTIC_MODALITY/VB • So far Pattern Matcher expects domains have only names.

  5. Example • Sentence: tpck/MM-MOLECULE/NN or L-NAME causes hemorrhagic_shock/MM-CONDITION/NN • Dependency: nsubj(causes-4, tpck/MM-MOLECULE/NN-5) -- dobj(case-4,hemorrhagic_shock/MM-CONDITION/NN-7) • Match: case-4(tpck/MM-MOLECULE/NN-5, hemorrhagic_shock/MM-CONDITION/NN-7)

More Related