102113Notes

Log

October 23 2013 Meeting

We discussed the three major user groups.

1. NLP Researchers - customize feature generation, argument identification, noise reduction, etc.
2. Power Users - use custom knowledge bases and relations
3. 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:

1. NEL-capability for Argument Identification
2. Negative Examples
3. Noise Reduction Component

We decided to follow Mitchell's suggestion and use Stanford CoreNLP's native data structures when appropriate

Milestones/Goals

1. Generate Distant Supervision data from preprocessed corpus. (10/29)
2. Run Preprocessing code on new textual data (1/1)
3. Provide Interface for NEL with external KB in Argument Identification (11/6)
4. Run Original Multir Algorithm with new implementation (11/8)
5. Run Multir with NEL-Argument Identification
6. Extend Preprocessing interface to allow for custom preprocessing schemes
7. Establish working web-demo
8. Add noise-reduction component and negative example components