Difference between revisions of "User:Emayfiel"
(Created page with 'My name is Elijah Mayfield. I'm coming into this course with a language technologies background. I'm a first-year Ph.D. in LTI, though I've been around CMU for awhile before this…') |
|||
| (12 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
For information on recent research and publications, visit [http://www.cs.cmu.edu/~emayfiel my webpage]. You'll also potentially be interested in [http://www.cs.cmu.edu/~cprose/SIDE.html SIDE], a toolkit I maintain for text mining, which extends Weka's capabilities with numerous tools for feature extraction and error analysis. | For information on recent research and publications, visit [http://www.cs.cmu.edu/~emayfiel my webpage]. You'll also potentially be interested in [http://www.cs.cmu.edu/~cprose/SIDE.html SIDE], a toolkit I maintain for text mining, which extends Weka's capabilities with numerous tools for feature extraction and error analysis. | ||
| − | + | My project for this course will be [[Stylistic Structure in Historic Legal Text]] with [[User:Yww|William Y. Wang]]. | |
| + | |||
| + | === Wiki Writeups: === | ||
| + | |||
| + | '''Round 1''' | ||
| + | |||
| + | [[Barzilay and Elhadad, 2003]] | ||
| + | |||
| + | [[Morante et al., 2010]] | ||
| + | |||
| + | [[Munteanu and Marcu, 2006]] | ||
| + | |||
| + | [[Farkas et al., 2010]] | ||
| + | |||
| + | '''Round 2''' | ||
| + | |||
| + | [[Bootstrapping]] - Method | ||
| + | |||
| + | [[Pattern Matching over Annotations]] - Method | ||
| + | |||
| + | [[Boguarev and Neff, 2010]] | ||
| + | |||
| + | [[Riloff et al., 2003]] | ||
Latest revision as of 01:43, 30 November 2011
My name is Elijah Mayfield. I'm coming into this course with a language technologies background. I'm a first-year Ph.D. in LTI, though I've been around CMU for awhile before this. In general, I work on conversation analysis, discourse and dialogue, with a special emphasis on sociolinguistics and applying insights from the social sciences in a way that can be reproduced reliably by automated means.
Obviously, structured prediction for linguistic data might be helpful for these tasks.
For information on recent research and publications, visit my webpage. You'll also potentially be interested in SIDE, a toolkit I maintain for text mining, which extends Weka's capabilities with numerous tools for feature extraction and error analysis.
My project for this course will be Stylistic Structure in Historic Legal Text with William Y. Wang.
Wiki Writeups:
Round 1
Round 2
Bootstrapping - Method
Pattern Matching over Annotations - Method
