Page Comparison

...

1. Create an initial set of system and user utterances. Each utterance needs to be associated to an identifying string (like a name), usually referred to as speech act. The natural language understanding (NLU), dialog management (DM) and natural language generation (NLG) modules will use these identifiers instead of the real utterances.
2. Create a dialogue policy. This policy consists of:
   
   1. the set of variables that constitute the dialogue state (the dialogue manager is an information based one. That is it decides what to say based on what the user said and the current state of the conversation as represented in the dialogue state (also called information state)). 
      The information state can also contain: forward inference rules (e.g. brother(x,y)=>sibling(x,y)) and predications like brother(Person1,Person2).
   2. the set of sub-dialogue networks. These sub-dialogues are similar to planning operators, with preconditions and effects. The dialogue manager (DM), will select one based on what the user said and the current dialogue state. Each sub-dialogue typically carries out a short portion of an entire dialogue (e.g. the greeting phase, or answering a question). sub-dialogues roughly corresponds to functions in programs, if a set of dialogue steps often happen together and multiple times, it's worth grouping them into a sub-dialogue.
3. Train the natural language understanding module to map a given utterance to one of the known identifying strings (speech acts) defined in the first step.

The entire information that defines a character, e.g. CakeVendor, for the FLoReS system is defined in a set of files sitting in the directory resources/characters/CakeVendor/.

This directory contains three sub-directories that parallel the 3 steps defined above:

...