Digital Signal Processing Reference
In-Depth Information
Figure 1-3.
Task distribution of the corpus.
3.
LAYERED INTENTION TAG
To develop a spoken dialogue system based on speech corpus [4]‚ certain
pre-specified information is required for each sentence corresponding to a
particular response of the system. Additionally‚ to perform the response to
satisfy the user‚ we need to presume the intention of the user's utterances.
From our preliminary trials‚ we have learned that user's intention has a wide
range even for a rather simple task‚ which could necessitate the creation of
dozens of intention tags. To organize and expedite the process‚ we have
stratified tags into several layers‚ which have resulted in an additional benefit
of a hierarchical approach in analyzing users' intentions.
Our Layered Intention Tags (LIT) are described in Table 1-5 and the
structure is shown in Figure 1-4. Each LIT is composed of four layers. The
discourse act layer signifies the role of the speech unit in a given dialogue‚
which are labeled as “task independent tags”. However‚ some units do not
have a tag at this layer.
Action layer denotes the action taken. Action tags are subdivided into
“task independent tags” and “task dependent tags”. “Confirm” and “Exhibit”
are task independent‚ whereas “Search”‚ “ReSearch”‚ “Guide”‚ “Select” and
“Reserve” are the task dependent ones.
Object layer stands for the objective of a given action including “Shop”‚
“Parking.”
Finally‚ the argument layer denotes other miscellaneous information about
the speech unit. Argument layer is often decided directly from some specific
keywords in a given sentence. As it is shown in Figure 1-4‚ the lower layered
intention tags are explicitly depended on the upper layered ones.
