Sixth European Conference on Speech Communication and Technology
The work presented in this
paper regards the construction of the formal representation of the content
ofthe input sentence. It is part of a speech-to-speech translation system,
where this language independent format is used as an intermediate representation
between source and target languages. The general application domain is
travel planning, but it is divided in more specific domains, such as hotel
and transport reservation. Starting from the word string output by the
recognizer, the construction of the content representation requires the
1) the speech act and concept list, and
2) a list of arguments in the form of argument name/value pairs.
For the former, semantic classification trees  are used and domain portability depends on the availability of labeled data for the new domain. For argument extraction a pipeline of filters is used, where each filter is based on a semantic grammar, which in most cases is regular. Then, these filters can be used all together for the most general analysis, or separately when only one or a few domains are considered. Argument extraction is described and evaluated in terms of the changes in precision and recall with respect to the number of filters and of rules.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Corazza, A. (1999): "An inter-domain portable approach to interchange format construction", In EUROSPEECH'99, 2419-2422.