TAILIEUCHUNG - Báo cáo khoa học: "Computational properties of environment-based disambiguation"

The standard pipeline approach to semantic processing, in which sentences are morphologically and syntactically resolved to a single tree before they are interpreted, is a poor fit for applications such as natural language interfaces. This is because the environment information, in the form of the objects and events in the application’s runtime environment, cannot be used to inform parsing decisions unless the input sentence is semantically analyzed, but this does not occur until after parsing in the single-tree semantic architecture. . | Computational properties of environment-based disambiguation William Schuler Department of Computer and Information Science University of Pennsylvania Philadelphia PA 19103 schuler@ Abstract The standard pipeline approach to semantic processing in which sentences are morphologically and syntactically resolved to a single tree before they are interpreted is a poor fit for applications such as natural language interfaces. This is because the environment information in the form of the objects and events in the application s runtime environment cannot be used to inform parsing decisions unless the input sentence is semantically analyzed but this does not occur until after parsing in the single-tree semantic architecture. This paper describes the computational properties of an alternative architecture in which semantic analysis is performed on all possible interpretations during parsing in polynomial time. 1 Introduction Shallow semantic processing applications comparing argument structures to search patterns or filling in simple templates can achieve respectable results using the standard pipeline approach to semantics in which sentences are morphologically and syntactically resolved to a single tree before being interpreted. Putting disambiguation ahead of semantic evaluation is reasonable in these applications because they are primarily run on content like newspaper text or dictated speech where no machine-readable contextual information is readily available to provide semantic guidance for disambiguation. This single-tree semantic architecture is a poor fit for applications such as natural language interfaces however in which a large amount of contextual information is available in the form of the ob jects and events in the application s run-time environment. This is because the environment information cannot be used to inform parsing and disambiguation decisions unless the input sentence is semantically analyzed but this does not occur until after

• Báo cáo khoa học
• Computational properties
• environment based disambiguation
• William Schuler
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Journal of Chemistry
• Metallo phthalocyanines
• Cyclic voltammetry
• Computational chemistry
• Photodynamic therapy
• Photochemical properties
• Computational fluid dynamics
• RANS k ω SST model
• Molten salt reactor
• Liquid fuel molten salt reactor
• FLiNaK’s thermophysical properties
• Physico chemical
• The mechanical properties
• Interlaminar
• intralaminar properties
• Interlaminar fracture toughness
• ASCI alliance center
• Simulation of dynamic response
• Materials FY 2000 annual report
• Solid dynamics
• Materials properties
• Compressible turbulence
• Computational science
• K shell decomposition
• Coexpression network
• Computational biology
• BrainSpan coexpression
• RNA seq
• BMC Chemistry
• Molecular modeling
• Glycating carbonyl compounds
• Maillard reaction
• Conceptual DFT
• Chemical reactivity theory
• UV visible absorption spectroscopy
• Substituent effect
• Solvent effect
• Density functional theory (DFT)
• Time dependent density functional theory
• Density functional theory
• Differential pulse voltammetry
• Antidiabetic properties
• Chemical carcinogens
• Schiff base
• Electronic properties
• Synthesis techniques
• Antineoplastic activity
• DPPH radical scavenging activity
• Copper complex
• X ray
• Computational analysis
• Cu(II) complex compound
• Highest occupied molecular orbital (HOMO)
• Molecular electrostatic potential surface (MEPS)
• Soluble metallophthalocyanine
• Nanocomposite film
• Geometry optimization
• X ray diffraction
• Scanning electron microscopy
• BMC Bioinformatics
• Protein sequence
• Physicochemical property
• Amino acid
• Machine learning
• Bayesian network
• Support vector machine
• BMC Musculoskeletal Disorders
• Bone fracture healing
• Inflammatory stage
• Initial callus size
• Granulation tissue material properties
• Migration rate
• Mechanobiological modeling