This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft-website.git
The following commit(s) were added to refs/heads/master by this push:
new 791ec09 Update intent-matching.html
791ec09 is described below
commit 791ec09ca4c8bb6dcd91fe7d107346d7096b83eb
Author: Aaron Radzinski <[email protected]>
AuthorDate: Mon Sep 21 20:22:35 2020 -0700
Update intent-matching.html
---
intent-matching.html | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/intent-matching.html b/intent-matching.html
index 5ce23fa..4b75d43 100644
--- a/intent-matching.html
+++ b/intent-matching.html
@@ -311,6 +311,40 @@ id: intent_matching
<li><code>elm1</code>('A', 'B') <code>freeword</code>('C')
<code>elm3</code>('D')</li>
<li><code>freeword</code>('A') <code>elm2</code>('B', 'C')
<code>elm3</code>('D')</li>
</ol>
+ <p></p>
+ <p>
+ Note that at this point the system cannot determine which
of these variants is the best - there's simply not
+ enough information at this stage. It can only be
determined when matched against model's intents - which
+ will happen in the next step.
+ </p>
+ </li>
+ <li>
+ <b>Step: 5</b><br>
+ <p>
+ At this step the actual matching between intents and
variants happens. Each parsing variant from the previous
+ step is matched against each intent. Each matching pair of
a variant and an intent produce a match with a
+ <em>certain weight</em>. If there are no matches at all -
an error is returned. If there are matches, the match
+ with the biggest weight is selected as a winning match.
The intent's callback from the winning match is
+ than called.
+ </p>
+ <p>
+ Although details on exact algorithm on weight calculation
are too complex, here's the general guidelines
+ on what determines the weight of the match between a
parsing variant and the intent:
+ </p>
+ <ul>
+ <li>
+ A match that captures more tokens has more weight than
a match with less tokens. As a corollary, the match
+ with less free words has bigger weight than a match
with more free words.
+ </li>
+ <li>
+ Tokens for user-defined elements are more important
than built-in tokens.
+ </li>
+ <li>
+ A more specific match has bigger weight. In other
words, a match that uses token from the conversation
+ context (an STM) has less weight than a match that
only uses tokens from the current request. In the same
+ way older tokens from the conversation produce less
weight than the younger ones.
+ </li>
+ </ul>
</li>
</ul>
</section>
