Difference between revisions of "Iarpa"
From Knowitall
| Line 1: | Line 1: | ||
| + | == Domain Recognizers == | ||
| + | |||
| + | == Rule Learning == | ||
| + | |||
| + | == Quality of Extractions == | ||
| + | * Too short relations (2 characters) | ||
| + | * Too long relations (7 words) | ||
| + | * some args are just special symbols (e.g., ") | ||
| + | * Pronoun Resolution | ||
| + | |||
== Speed == | == Speed == | ||
* Compile to native code. | * Compile to native code. | ||
* Compare NLP libraries. | * Compare NLP libraries. | ||
| − | == | + | == Conversion of Docs to Text == |
| − | + | * Detect headlines and handle separately | |
| − | + | * Sentences with only single letters | |
| − | * | + | * Detect bullet points |
| − | * Sentences with only single letters | ||
| − | * | ||
Revision as of 01:36, 21 December 2010
Contents
Domain Recognizers
Rule Learning
Quality of Extractions
- Too short relations (2 characters)
- Too long relations (7 words)
- some args are just special symbols (e.g., ")
- Pronoun Resolution
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
