TAILIEUCHUNG - 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 .

• Báo cáo khoa học
• Robust
• Finite State Parsing
• Spoken Language Understanding
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Journal of Automation and Control Engineering
• Asynthesis method of robust cascade control system
• Robust cascade control system
• Imposes robust conditions
• Soft oscillation index
• Robust simulation optimization using φ divergence
• Robust simulation optimization
• Less simulation runs
• Robust optimization φ divergence
• Model based approach
• Command shaped robust control of a flexible spacecraft
• Command shaped robust control
• Strong cross couplings
• Loop shaping design
• International Journal of computer science & communication networks
• Robust video watermarking scheme in DWT domain
• Robust video watermarking scheme
• Selective row extraction
• The watermarked video
• Method three rows
• The robust ASR using uncertainty of observation techniques
• The robust ASR
• The robustness of ASR however
• Automatic speech recognition
• Indentification and robust control
• Towing rope system
• Robust control
• PID control
• Non linear system
• Novel robust chance constrained possibilistic programming model
• Disaster relief logistics under uncertainty
• Multi objective robust possibilistic programming model
• Relief distribution minimizing
• Metamodel based robust
• Black box simulation optimization
• Designing and Analyzing of Computer Experiments
• Metamodel Based Robust Simulation Optimization
• Dual response methodology
• International Journal of Computer Science and Communication Networks
• Robust watershed segmentation of noisy image using wavelet
• Robust watershed segmentation
• Noisy image using wavelet
• Few energy transform values
• Marker controlled Watershed Segmentation
• DC – DC converter
• Switched system
• Autonomous switched systems
• Robust technique control
• AC DC power converters
• Robust finite time supoptimal control
• Robust finite time supoptimal control of large scale systems
• Finite time control
• Large scale system
• State and control delay
• Linear matrix inequality
• Robust subspace tracking algorithms in signal processing
• Robust subspace tracking algorithms
• Non Gaussian noises
• Streaming PCA
• Subspace tracking
• Linear time delay systems
• Stability
• Robustness
• delay dependent robust stability
• LyapunovKrasovskii functional
• Advanced In Vehicle
• Spoken Dialog Corpus
• Dialogue System
• Robust Dialog Management
• Correcting Code
• Robust Speech Recognition
• Fast and Robust
• Part of Speech Tagging
• Dynamic Model Selection
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Robust Conversion
• CCG Derivations
• Phrase Structure Trees
• Probabilistic Integration
• Partial Lexical Information
• Noise Robust Haptic Voice Recognition
• A Bayesian Method
• Robust Estimation
• Distributional Similarities
• Towards robust multi tool tagging
• An OWL DL based approach
• Christian Chiarcos
• Creating Robust Supervised Classifiers
• Web Scale N gram Data
• Shane Bergsma
• Pointwise Prediction for Robust
• Adaptable Japanese Morphological Analysis
• Graham Neubig
• Semantic Information and Derivation Rules
• Robust Dialogue Act Detection
• a Spoken Dialogue System
• Robust Machine Translation Evaluation
• Entailment Features
• o Sebastian Pad
• Creative Language Retrieval
• A Robust Hybrid
• Information Retrieval
• Linguistic Creativity