'Information Retrieval' Category
POTW: 3/11/07: “COGEX: A Logic Prover for Question Answering” by Moldovan, et. al.
Following on from last weeks look at Language Computer Corporations TREC 2003 entry, we are going to dig deeper into the theorem prover part of the system and look at “COGEX: A Logic Prover for Question Answering” by Moldovan, et. al.
POTW 3/4/07: Answer Mining by Combining Extraction Techniques with Abductive Reasoning by Harabagiu, et. al.
This weeks paper, “Answer Mining by Combining Extraction Techniques with Abductive Reasoning“, lays out, at a high level, the capabilities of the highest performing QA system at TREC 2003, namely Language Computer Corporation’s QA system. The first section or two lay out the groundwork for the competition, much as was already done in the Voorhees [...]
POTW 2/26/07: Overview of the TREC 2003 Question Answering Track by Voorhees
Overview of the TREC 2003 Question Answering Track by Voorhees is a nice introduction to the QA task, as defined by TREC. The first two sections layout the two main tasks: The Passages Task Main Task – Divided into three sub tasks Factoids Lists Definitions The passages task is used to test whether a QA [...]
POTW 2/11/07: Discussion of sections 5-8 of Minkov, et. al
POTW 2/11/07: Contextual Search and Name Disambiguation in Email Using Graphs Discussion of Sections 5 through 8 The remaining sections of this paper are discussions of two applications of the algorithms plus the body of related work and conclusions that can be drawn from the work. Section 5 gives the details on what corpora were [...]
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 [...]