Difference between revisions of "Vulcan/SystemStatus"

From Knowitall
Jump to: navigation, search
(Inference Components)
Line 8: Line 8:
 
[[File:Sys-arch-online.jpg|frame|center|alt=System Architecture|System Architecture: Online components]]
 
[[File:Sys-arch-online.jpg|frame|center|alt=System Architecture|System Architecture: Online components]]
  
== Weak Evidence Finder ==
+
=== Weak Evidence Finder ===
 +
Greg is going to be developing this component.
  
 
[[File:weak-evidence-finder.jpg|frame|center|alt=Weak Evidence Finder Details|System Architecture: Weak Evidence Finder]]
 
[[File:weak-evidence-finder.jpg|frame|center|alt=Weak Evidence Finder Details|System Architecture: Weak Evidence Finder]]

Revision as of 20:22, 20 August 2013

The system consists of Inference (online) and Axiom and Rule generation (offline) components.

Inference Components

System Architecture
System Architecture: Online components

Weak Evidence Finder

Greg is going to be developing this component.

Weak Evidence Finder Details
System Architecture: Weak Evidence Finder

Status

Component Description I/O Status To Do
Proposition Extractor Extracts propositions to be verified by the system Input: Sentence asserting the answer choice.
Output: A proposition represented as a open IE tuple.
Stub implemented: Sentence piped into Open IE 4.0. Output tuples that fit a specified pattern are converted into a proposition. Select the best tuple. Stem, normalize, extract polarity, handle n-ary tuples.
Evidence Finder Provides evidence for the input proposition using weaker methods. Input: Proposition
Output: Rules/Axioms that derive the proposition (in one-step) weighted according to the confidence provided by each method.
Tuple matcher implementation underway. Uses Open IE solr instance to find matching sentences/tuples.
Pattern matcher not implemented.
Jena evidence finder partly implemented. Produces a single derivation, which needs to be converted to axioms and rules. Note: Not using Jena as a evidence finder anymore. Tuffy is optimized for efficient inference.
Implement pattern matching, improve tuple matching, add scores.
MLN Instance Generator Converts the evidence into MLN input format. Input:Axioms/Rules from weaker methods.
Output:Translated into Tuffy's input format.
Stub implemented: Does a faithful translation to MLN syntax. Fix bug in predicate definitions.
End-to-End Driver Command line application. Input: Sentence asserting an answer choice.
Output:Score
Stub implemented. Create web interface.

Axiom and Rule Generation Components

System Architecture
System Architecture: Offline components
Component Description I/O Status
Axioms Extractor Generates axioms from multiple knowledge sources. Input:
Output:
None.
Rules Generator Uses second order rule templates to generate first-order inference rules. Input:
Output:
None.