'Machine Learning' Category
POTW 2/11/07: Discussion of sections 1-4 of Minkov, et. al
Intro
This week we are reading Contextual Search and Name Disambiguation in Email Using Graphs
by Einat Minkov, William W. Cohen and Andrew Y Ng, all of Carnegie Mellon University. Like the past few papers, this paper also focuses on how to use graph theory to solve some common NLP papers. Unlike the past few [...]Popularity: 7% [?]
Discussion of Section 3 of TextRank
Section 3 of TextRank: Bringing Order Into Texts covers the first application of the TextRank approach proposed in section 2. The authors have chosen keyword extraction to demonstrate the capabilities of the approach. Keyword extraction is the problem of determining the keywords that best describe a document. It can be thought of as a precursor [...]
Popularity: 6% [?]
Discussion of Joachims (SVMs)
This week, if you remember, we are discussing Text Categorization with Support Vector Machines: Learning with Many Relevant Features - Joachims (ResearchIndex), which is a paper on Text Categorization (one of the most cited such papers on Google Scholar under the Text Categorization search).
Text Categorization is the problem of assigning one or more predefined categories [...]Popularity: 5% [?]
Text Categorization with Support Vector Machines: Learning with Many Relevant Features - Joachims (ResearchIndex)
Text Categorization with Support Vector Machines: Learning with Many Relevant Features - Joachims (ResearchIndex)
Week 2, as promised, is another Text Categorization topic, and this one is pretty big, receiving over 1500 cites according to Google Scholar. I know a little bit (little being the operative word) about SVMs (Support Vector Machines) so it will be [...]Popularity: 3% [?]
Discussion of Sections 5-7 of Yang 97
Whew, I think we’ve made it through our first paper, or we are about to anyway. If you recall, we are working our way through Yang 97 and had made it through the first 4 sections so far, which are covered here. This leaves us with the meat of the paper, I guess, which is [...]
Popularity: 5% [?]

