Model of Dialog<BR>
-- Prediction of the Next Topic Based on Utterance Motivation --
<P>
Riichiro MIZOGUCHI and Yoichi YAMASHITA
<P>
The Institute of Scientific and Industrial Research, Osaka University<BR>
8-1, Mihogaoka, Ibaraki, Osaka, 567 JAPAN<BR>
e-mail: miz@ei.sanken.osaka-u.ac.jp
<P>
Prediction of user's next utterances is an important technique to 
understand spoken dialog with the middle or large size vocabulary.  
Various kinds of dialog knowledge, such as utterance pairs, topics, 
and so on, are indispensable for prediction of the utterances.  We 
have proposed a basic mechanism for utterance prediction last year.  
It was based on a topic transition model, named TPN (topic packet 
network).  The topic information was very useful to predict the 
utterances.  TPN is a static model of topic transitions represented 
in the form of a sort of network.  In a TPN, topic packets (TP) 
bundle some topics and they are a priori linked each other.  However, 
the topic of the utterance dynamically changes in a dialog as the 
dialog goes on.  It is not easy to describe all the possible topic 
transitions in a static network especially for dialog tasks with the 
large vocabulary.  A dynamic mechanism is appropriate for modeling 
topic transitions.  In this year, we have discussed a new mechanism 
for enumerating possible topics of the next utterance by introducing 
a model of utterance motivation.  
<BR>
In a goal-oriented dialog, we carry out a dialog in order to exchange 
focussed information.  Goals are achieved step by step through repeated 
interactions.  We usually have a definite motivation of making an 
utterance in such a dialog.  This motivation of the utterance has a 
close connection with the meaning of the utterance.  A model of the 
utterance motivation is expected to flexibly predict topics in a dialog.  
<BR>
We analyzed several dialogs concerning a task of route direction and 
trip reservation in order to investigate motivations of the utterance.  
Since it was assumed that a stimulus and a response in an utterance pair 
have the same topic, only the stimuli were analyzed.  For example, 
'to make a comparison because an attribute has multiple values' is a 
motivation.  Motivations could be divided into two different levels of 
motivation: communication and problem solving.  The motivation of 
communication is triggered by the state of information exchange.  A 
state that 'an attribute has multiple values' is categorized into one 
of the motivations of this level.  The motivation of problem solving is 
related to how to use the derived information in the process of problem 
solving.  'To make a comparison' is an example of the motivations of 
problem solving.  
<BR>
The motivations of communication are classified into 8 categories as 
follows.  
<P>
        \=a. A value is unknown<BR>
	\>b. A value is ambiguous<BR>
	\>c. An attribute has multiple values<BR>
	\>d. An attribute or an action is unknown<BR>
	\>e. Attributes or actions are exhausted<BR>
	\>f. An object or an action sequence is ambiguous<BR>
	\>g. To confirm something uncertain<BR>
	\>h. An object or an action sequence is unknown
<P>
<BR>
Knowledge about the dialog domain is necessary for the dialog manager to 
know transferred information in a dialog.  The dialog manager predicts 
the motivations of communication based on the state of transmission for 
each piece of information.  We introduced two kinds of information 
packets to organize the domain knowledge.  The 'action sequence' 
represents a sequence of actions which are executed in order to achieve 
a goal.  The 'object' describes an assembly of information except for 
action sequences.  
<BR>
The motivations of problem solving are classified into 10 categories as 
follows. 
<P>
        \=A. To compare<BR>
	\>B. To select<BR>
	\>C. To sort<BR>
	\>D. To know/inform the reason<BR>
	\>E. To know/inform the condition<BR>
	\>F. To know/inform the related information<BR>
	\>G. To correct<BR>
	\>H. To satisfy the constraints<BR>
	\>I. To know/inform the goal<BR>
	\>J. To know/inform the completion
<P>
<BR>
The purpose in the problem solving process by the user invokes the 
motivation of this level.  A user modeling is a very important technique 
to predict the motivation of problem solving.  This is future work.  
<BR>
The motivation of an utterance is modeled by combination of two levels 
of the motivation mentioned above.  We investigated the frequency of 
combined motivations using 6 simulated dialogs.  The tasks of two sets 
of dialog are route direction and trip reservation, respectively.  All 
combinations of motivation did not occur and there was a small 
difference of distribution of the frequency between the two tasks.  
<BR>
A mechanism for predicting topics in the next utterance is described 
according to each utterance motivation.  Assume that a slot of an 
information packet contains multiple values and 'to compare' is 
predicted as the motivation of problem solving.  The motivation 'c' is 
predicted based on the state of communication.  Thus, the combination 
'c' and 'A' is identified as the motivation of the next utterance.  
The topic prediction pattern for the motivation 'cA' is to enumerate 
topics in the information packet subordinated by the slot which 
contains multiple values.  
<BR>
The former mechanism based on the TPN model had poor flexibility to 
dynamic change of dialogs.  A model of the utterance motivation enables 
utterance prediction adaptive to situations in a dialog.  Evaluation 
of the proposed mechanism remains an issue to be discussed.  
<P>
Keywords: utterance prediction, utterance motivation, 
topic transition model, spoken dialog recognition