Information Technology Reference
In-Depth Information
/
**
TOPIC: REGIONS
**
/
Plan {
NAME: 'askFor-homeTown'
GOAL: get user's home town
BODY: <act> Where are you from? </act>
...}
Plan {
NAME: 'tell-favoriteCountry'
GOAL: tell system's favorite country
BODY: <act> I love Portugal. </act>
...}
/
**
TOPIC: SPORTS
**
/
Plan {
NAME: 'reply-likingSports'
GOAL: tell system's interest in sports
BODY: <act> Yes, I like soccer. </act>
...}
/
**
TOPIC: POLITICS
**
/
Plan {
NAME: 'askFor-politicalAttitude'
GOAL: get user's party affiliation
BODY: <act> What's your preferred
political party? </act>
...}
The topical classification of the rules allows their execution based on the dialog situ-
ation. Given a first encounter, the dialog participants would not talk about their political
affiliation, for instance. Accordingly, Max avoids making use of the rules dealing with
so-called
unsafe topics
. That is, he neither uses such a rule pro-actively raising a topic
nor reactively to answer a user question. Regarding the latter, he rather gives an evasive
answer (as shown in Figure 4).
5
The Dialog Scenario
In our scenario, a human participant has a face-to-face small talk encounter with the
virtual agent Max. Thereby, the human dialog partner expresses him or herself via
keyboard-based text inputs whereas the artificial interlocutor answers with spoken lan-
guage based on speech synthesis. Thus, the contributions of either side exist as textual
information redundantizing additional speech recognition processes. Moreover, prepro-
cessing steps to handle incomplete and non-standard sentences are not required as typed
inputs mostly consist of complete sentences containing only little abbreviations and
slang expressions. However, textual inputs preclude the perception of topic ending in-
dicators such as repetitions, pauses, laughter, etc. [18]. Thus, they can not be considered
in the process of topic detection although often used in human conversation.
