Difference between revisions of "User:Fkeith"

From Cohen Courses
Jump to navigationJump to search
Line 22: Line 22:
 
* [[Daume ICML 2009|"Unsupervised Search-based Structured Prediction", Hal Daume III, ICML 2009]]
 
* [[Daume ICML 2009|"Unsupervised Search-based Structured Prediction", Hal Daume III, ICML 2009]]
 
* [[Practical very large CRFs|"Practical very large scale CRFs". Lavergne, T., O. Cappé, and F. Yvon.  ACL-2010.]]
 
* [[Practical very large CRFs|"Practical very large scale CRFs". Lavergne, T., O. Cappé, and F. Yvon.  ACL-2010.]]
* (New!) [[Machine Transliteration|"Machine Transliteration", K. Knight and J. Graehl, CL 1998]]
+
* [[Machine Transliteration|"Machine Transliteration", K. Knight and J. Graehl, CL 1998]]
* (New!) [[Accurate Unlexicalized Parsing|"Accurate Unlexicalized Parsing", D. Klein and C. D. Manning, ACL 2003]]
+
* [[Accurate Unlexicalized Parsing|"Accurate Unlexicalized Parsing", D. Klein and C. D. Manning, ACL 2003]]
 +
* (New!) [[Charniak and Johnson 2005|"Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking", Eugene Charniak, Mark Johnson, ACL 2005]]
 
=== Methods ===
 
=== Methods ===
 
* [[SEARN]]
 
* [[SEARN]]
=== In Progress ===
+
* (New!) [[Minimum error rate training]]
* [[Minimum error rate training]]
 
* [[Charniak and Johnson 2005|"Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking", Eugene Charniak, Mark Johnson, ACL 2005]]
 

Revision as of 10:10, 14 November 2011

Francis Keith

Francis-keith-headshot.jpg

Who Am I

I'm a student in the LTI, working part-time on a Master's degree. The rest of the time I'm a software engineer at M*Modal in Squirrel Hill. We create software for medical transcription and other medical applications. We have begun fairly recently to do more NLP-related tasks.

I'm in this class because I enjoy learning about various different machine learning applications. Plus, I'm hoping to pick up some new and different techniques to help M*Modal's NLP team.


Project

As of right now, my project will be based around using structured prediction methods to aid in automated extraction of templates for information extraction (very meta).

Click here for more info!

Wiki pages

Papers

Methods