102113Notes
From Knowitall
Log
October 23 2013 Meeting
We discussed the three major user groups.
- NLP Researchers - customize feature generation, argument identification, noise reduction, etc.
- Power Users - use custom knowledge bases and relations
- Novice User - uses out of the box system
The better the system is for the Novice user the more successful this project will be.
Some Important Requirements we discussed:
- NEL-capability for Argument Identification
- Negative Examples
- Noise Reduction Component
We decided to follow Mitchell's suggestion and use Stanford CoreNLP's native data structures when appropriate
Milestones/Goals
- Generate Distant Supervision data from preprocessed corpus. (10/29)
- Run Preprocessing code on new textual data (1/1)
- Provide Interface for NEL with external KB in Argument Identification (11/6)
- Run Original Multir Algorithm with new implementation (11/8)
- Run Multir with NEL-Argument Identification
- Extend Preprocessing interface to allow for custom preprocessing schemes
- Establish working web-demo
- Add noise-reduction component and negative example components