Difference between revisions of "Iarpa"
From Knowitall
| Line 1: | Line 1: | ||
| − | |||
| − | |||
| − | |||
| − | |||
== Quality of Extractions == | == Quality of Extractions == | ||
=== TODO === | === TODO === | ||
| − | * | + | == Engineering Tasks == |
| − | * | + | * Handle capital sentences. |
| − | * | + | * Handle geotagging and other oddities of the classified data. |
| + | * Address efficiency issues. | ||
| + | |||
| + | == Research Tasks == | ||
* Pronoun Resolution | * Pronoun Resolution | ||
| + | |||
=== DONE === | === DONE === | ||
* Too short relations (2 characters) | * Too short relations (2 characters) | ||
Revision as of 19:17, 4 April 2011
Contents
Quality of Extractions
TODO
Engineering Tasks
- Handle capital sentences.
- Handle geotagging and other oddities of the classified data.
- Address efficiency issues.
Research Tasks
- Pronoun Resolution
DONE
- Too short relations (2 characters)
Tools
Speed
- Compile to native code.
- Compare NLP libraries.
Conversion of Docs to Text
- Detect headlines and handle separately
- Sentences with only single letters
- Detect bullet points
