Situation
I have a set of references (please confer to bellow) in plain text format. And I want to reconstruct it into bibtex.
[19]T N Pornsin-Sirirak?S W Lee?H Nasse et al. MEMS wing technology for a battery-Powered omit ho Per. Proceeding 13th IEEE Annual International Conference on MEMS 2000?Miyazaki, Japan, 2000:799?804.
[20] E. Wong, F. Bourgault and T. Furukawa, Optimal multi-vehicle search for multiple lost targets in a Bayesian world, IEEE International Conference on Robotics and Automation paper, 2005, 31803185.
[21]L.A.Young, et. al. Use of Vertical Lift Planetary Aerial Vehicles for the Exploration of Mars.http://www.lpi.usra.edu/meetings/robomars/pdf/6227.pdf, 2003.
[23]M Sitti? D Campolo? J Yan? et. al. Development of PZT and PZN- PT based Unimorph actuators for micromechanical flapping mechanisms .In Proc of the IEEE Int Conf. on Robotics and Automation?Korea?2001.
Of course, firstly, I need to extract the records out of each entry. Generally, it is in the pattern of:
[digit] authorName. [authorName1. ...] title. kindOfPapers. [address.] date. [page.]
The record in bracket may be available or missed. In order to extract the information correctly, my sense is I should judge whether a record avaliable. It's best I can map each record in every entry to any of authorName
, title
, address
and data
and so on. After that I can replace the template of bibtex directly and precisly.
However, I am totally blank when it comes to Text Analysis
.
My Problem
What technique do I need to extract the record of an entry from semantics? Shall I need some data set or dictionary to train something?
Thanks.