Malarkodi C. S., Lex Elisabeth, Sobha Lalitha Devi
2016
Named Entity Recognition for the Agricultural Domain
17th International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2016); Research in Computing Science CICLING 2016 Springer Lecture Notes in Computer Science Konya, Turkey
Agricultural data have a major role in the planning and success of
rural development activi
ties. Agriculturalists, planners, policy makers, gover
n-
ment officials, farmers and researchers require relevant information to trigger
decision making processes. This paper presents our approach towards extracting
named entities from real
-
world agricultura
l data from different areas of agricu
l-
ture using Conditional Random Fields (CRFs). Specifically, we have created a
Named Entity tagset consisting of 19 fine grained tags. To the best of our
knowledge, there is no specific tag set and annotated corpus avail
able for the
agricultural domain. We have performed several experiments using different
combination of features and obtained encouraging results.
Most of the issues
observed in an error analysis have been addressed by post
-
processing heuristic
rules, which
resulted in a significant improvement of our system’s accuracy