tailieunhanh - Báo cáo khoa học: "Robust, Finite-State Parsing for Spoken Language Understanding"

Human understanding of spoken language appears to integrate the use of contextual expectations with acoustic level perception in a tightly-coupled, sequential fashion. Yet computer speech understanding systems typically pass the transcript produced by a speech recognizer into a natural language parser with no integration of acoustic and grammatical constraints. One reason for this is the complexity of implementing that integration. | Robust Finite-State Parsing for Spoken Language Understanding Edward c. Kaiser Center for Spoken Language Understanding Oregon Graduate Institute PO Box 91000 Portland OR 97291 Abstract Human understanding of spoken language appears to integrate the use of contextual expectations with acoustic level perception in a tightly-coupled sequential fashion. Yet computer speech understanding systems typically pass the transcript produced by a speech recognizer into a natural language parser with no integration of acoustic and grammatical constraints. One reason for this is the complexity of implementing that integration. To address this issue we have created a robust semantic parser as a single finite-state machine FSM . As such its run-time action is less complex than other robust parsers that are based on either chart or generalized left-right GLR architectures. Therefore we believe it is ultimately more amenable to direct integration with a speech decoder. 1 Introduction An important goal in speech processing is to extract meaningful information in this the task is understanding rather than transcription. For extracting meaning from spontaneous speech full coverage grammars tend to be too brittle. In the 1992 DARPA ATIS task competition CMU s Phoenix parser was the best scoring system Issar and Ward 1993 . Phoenix operates in a loosely-coupled architecture on the 1-best transcript produced by the recognizer. Conceptually it is a semantic case-frame parser Hayes et al. 1986 . As such it allows slots within a particular case-frame to be filled in any order and allows out-of-grammar words between slots to be skipped over. Thus it can return partial parses as frames in which only some of the available slots have been filled. Humans appear to perform robust understanding in a tightly-coupled fashion. They build incremental partial analyses of an utterance as it is being spoken in a way that helps them to meaningfully interpret the acoustic evidence. To .