Abstract
In spoken language understanding systems, the interface between automatic speech recognition on the one hand and natural language understanding on the other hand often consists of word graphs: a compact representation of the sequences of words that the automatic speech recognition component hypothesises for a given utterance.In this chapter, it is shown how ‘standard’ parsing algorithms (which normally assume a string as input) can be generalized straightforwardly to accept such a word graph as their input.Furthermore, a general model for robust parsing is presented in which a word graph is annotated with (perhaps partial) results of the parser. A search algorithm is defined which selects the best sequence of analyses from this annotated word graph, provided an appropriate multi-dimensional score function is defined.Finally, a number of techniques is discussed which approximate the fully general search algorithm and experimental results are provided indicating that efficient approximations are possible with little or no reduction in concept accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
