1. Shock Progress & Direction

2. MetaMap Tokenized words for Mohammed – Enables him to test his new models for Pattern matcher Mallet Training Data for Laura – Enables her to work on creating a better version of MetaMap. – MetaMap currently has many concept annotation issues because the dictionary they use is so large. Concepts are frequently tagged incorrectly.

3. Mishaps & Solutions Mapping concepts to the phrases – Maddening XML Schema Makes it difficult to understand how the words & their POS’s in each phrase map to the concepts. – Created a model of the utterances, phrases and concepts to solve this problem. Used a DOM parser at first. Took about 15 minutes per xml file for 18 hours total. – Replaced with SAX parser which sped up progress. – Lesson learned: Do not use a DOM parser for a large document.

4. Next Task: Exploration of New Methods For Extracting Named Entities The XConc Suite – Corpus developer and annotator – Explore XConc as a MetaMap replacement for extracting named entities using event based annotation.