Differences

This shows you the differences between two versions of the page.

Link to this comparison view

cgss15:students:jiayil:polyanalyst:weeklymeetings:4_8_2016 [2016/04/08 19:26] (current)
jiayil created
Line 1: Line 1:
 +====== Megaputer Intelligence Weekly Meeting 4/8/2016 ======
  
 +===== Working with the New PolyAnalyst Dictionaries -- Ankit =====
 +
 +Morphology, Spellcheck and Phrase dictionaries will be covered. ​
 +
 +14 types of dics in PA:
 +
 +Entity extraction and sentiment analysis: Companies, Geo, Human, Org, WordClasses
 +
 +Keyword extraction: Statistics
 +
 +And one more category:
 +
 +Support 14 languages currently, with multiple dics in each. Language detection node is helpful here. 
 +
 +Index works on morphology dic, after that can add nodes such as SpellCheck, KeywordExtraction,​ SentimentA, etc. 
 +
 +Default morphology dic: 86289 words, including words that belong to different parts of speech. ​
 +
 +Different attributes of verb:
 +
 +**Example**:​ "The patient receives 100mg of medicine X each day. Last week she received 80mg per day due to reduced tolerance."​
 +
 +**Query**: lemma(verb_personthird_singular_present,"​receive"​)
 +
 +Can do keyword extraction, then generate a dataset, then import this dataset as a new dictionary. ​
 +
 +New task: decide order of nodes, entity extraction before keyword extraction, name of a person?
 +
 +xEntity extraction. Link analysis can be directional.
 +
 +Reach out for webinars: text analytics and pharmaceuticals. ​
 +Seminar for pharma companies in Bloomington,​ how to use text analytics in pharma. ​
 +
 +PA User Conference 2016: Oct.  ​
 +
 +Raffles: number of bugs reported each month 
cgss15/students/jiayil/polyanalyst/weeklymeetings/4_8_2016.txt ยท Last modified: 2016/04/08 19:26 by jiayil
 
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
Recent changes RSS feed Donate Powered by PHP Valid XHTML 1.0 Valid CSS Driven by DokuWiki