Science Environment for Ecological Knowledge
Ecoinformatics site parent site of Partnership for Biodiversity Informatics site parent site of SEEK - Home
Science Environment for Ecological Knowledge









 

 

 



KRSMSAHM Dec 2006 Breakout Notes

Difference between version 2 and version 1:

Removed line 1
-
Line 12 was replaced by lines 11-22
- *
+ * domain extension mining
+ ** demo of keyword and co-occurrence mining from corpus (eml text, textbook, papers)
+ ** how generate from this information or extend approach to construct domain extensions
+ *** visualize, summarize the data (in particular, a matrix of terms and their co-occurrence weight)
+ *** LTER controlled vocabulary as a starting point
+ *** obtain verb and adjective lists for keywords
+ *** explore how verb phrase can be used to name the relations between entities/characteristics
+ *** incorporate definitions from dictionary, wordnet, or glossaries for each entity
+ *** pre-classify the entities into classes based on part-of-speech tags
+ *** use look-up tables from common classes (measurement units, etc.)
+ *** profiling the data sources into various domains
+

Back to KRSMSAHM Dec 2006 Breakout Notes, or to the Page History.