Guys,
I'm still unable to generate speech from r2l-like output without having
the to-be-generated sentence and parse. As a result I cannot generate
speech of inferred knowledge.
Any idea of when this will be fixed? Is someone working on it? If not
maybe I should give it a stab (but I fear I may take a while cause I'm
not very familiar with the code).
See below for a way to reproduce the problem.
Nil
================
1. enter chatbot-psi
2. (chat "Robert likes chicken feet")
3. save in a file the SetLink corresponding to the r2l output
4. exist chatbot-psi
5. enter chatbot-psi
6. load the previously saved SetLink
7. (chat "Alice likes chicken feet")
8. (chat "What does Robert like")
the given answer is
Alive likes chicken feet
while, if NLG what doing a proper job, it should be
Robert likes chicken feet
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit
https://groups.google.com/d/msgid/opencog/57797AD0.2050807%40gmail.com.
For more options, visit https://groups.google.com/d/optout.
