Difference between revisions of "Vulcan/PrototypeToWorking"
From Knowitall
(→Switching to using actual evidence) |
|||
Line 13: | Line 13: | ||
: Import into postgres db. | : Import into postgres db. | ||
− | ; CNC [Stopgap arrangement until Postgres external procedure is figured out.] | + | ; Compound Noun Categorizer (CNC) [Stopgap arrangement until Postgres external procedure is figured out.] |
: Process arguments (phrases) in propositions and study guide through CNC. | : Process arguments (phrases) in propositions and study guide through CNC. | ||
Line 21: | Line 21: | ||
: Will do this early next week. | : Will do this early next week. | ||
− | |||
== Rules == | == Rules == |
Revision as of 06:12, 6 September 2013
Switching to using actual evidence
- Open IE tuples
- We need nested tuples. Open IE 4.0 handles n-ary but not nesting. [Michael will add post-processing to output nested tuples]
- Convert Open IE tuples into Tuffy's MLN axiom format.
- Decide on stemming, head word extraction and other normalization to apply.
- Import into postgres db.
- WordNet
- Convert WordNet RDF triples into Tuffy's MLN format.
- Import into postgres db.
- Compound Noun Categorizer (CNC) [Stopgap arrangement until Postgres external procedure is figured out.]
- Process arguments (phrases) in propositions and study guide through CNC.
- Extract relations that denote containment (e.g., "composed of")
- Figure out external procedures.
- Will do this early next week.
Rules
- Examples provide a starting point.
- Need to write a converter that translates human readable rules into MLN format.
- How to weight the rules?