Iarpa
From Knowitall
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