Difference between revisions of "Vulcan/SystemPrototype"
From Knowitall
(→Status) |
(→Status) |
||
| Line 10: | Line 10: | ||
== Status == | == Status == | ||
| − | * <b>Score</b> The system outputs scores for each query predicate. If query is not in output then score is zero. | + | The MLN programs and output from Tuffy can be found here. |
| + | |||
| + | * <b>Knowledge:</b> Worked out the facts and rules required. | ||
| + | * <b>Score: </b> The system outputs scores for each query predicate. If query is not in output then score is zero. | ||
| + | * <b>Does it work?</b> | ||
<blockquote> | <blockquote> | ||
| − | * | + | * In all three examples the correct answer is assigned higher score compared to the incorrect ones. |
| + | * Facts inferred by larger number of steps have a lower score compared to those inferred by a smaller number of steps. | ||
</blockquote> | </blockquote> | ||
| − | * <b> | + | * <b>What other diagnostics do we have?</b> |
| − | |||
| − | |||
<blockquote> | <blockquote> | ||
| − | * | + | * List inferred facts along with their probabilities. |
| − | * | + | * List the rules (first-order clauses in MLN lingo) that are reachable from the query fact. |
| − | |||
</blockquote> | </blockquote> | ||
| − | * <b> | + | * <b> What diagnostics do we NOT have?</b> |
<blockquote> | <blockquote> | ||
| − | * | + | * A reconstruction/visualization of the MLN network. |
| − | |||
| − | |||
| − | |||
</blockquote> | </blockquote> | ||
| − | * <b> | + | |
| + | * <b>What does this exercise suggest?</b> | ||
| + | |||
<blockquote> | <blockquote> | ||
| − | * | + | * <span style="background-color:yellow">Unable to materialize Nested tuples. Skipping this until this becomes necessary. The main reason we'd need this is to score the nested tuple. For now we can compute this from the score of its components: Score(nested_tuple) = Score(top tuple) * Score (nested)</span> |
| − | * | ||
</blockquote> | </blockquote> | ||
Revision as of 19:17, 27 August 2013
Overview
The prototype is designed to work on three questions. We want the system to output the following:
- Score for the input proposition.
- New facts inferred.
- Facts and rules used in scoring.
Status
The MLN programs and output from Tuffy can be found here.
- Knowledge: Worked out the facts and rules required.
- Score: The system outputs scores for each query predicate. If query is not in output then score is zero.
- Does it work?
- In all three examples the correct answer is assigned higher score compared to the incorrect ones.
- Facts inferred by larger number of steps have a lower score compared to those inferred by a smaller number of steps.
- What other diagnostics do we have?
- List inferred facts along with their probabilities.
- List the rules (first-order clauses in MLN lingo) that are reachable from the query fact.
- What diagnostics do we NOT have?
- A reconstruction/visualization of the MLN network.
- What does this exercise suggest?
- Unable to materialize Nested tuples. Skipping this until this becomes necessary. The main reason we'd need this is to score the nested tuple. For now we can compute this from the score of its components: Score(nested_tuple) = Score(top tuple) * Score (nested)
