• DocumentCode
    2769620
  • Title

    A Structured Context Model for Grammar Learning

  • Author

    Chang, Nancy ; Mok, Eva

  • Author_Institution
    California Univ., Berkeley
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    1604
  • Lastpage
    1611
  • Abstract
    We present a structured model of context that supports an integrated approach to language acquisition and use. The model extends an existing formal notation, embodied construction grammar (ECG), with representations for tracking both entities and events in discourse and situational context. The notation employs an intermediate level of granularity between low-level sensorimotor representations (such as that suitable for dynamic models of action and events for grounded language learning) and the more schematic representations needed for learning and using grammar. The resulting model allows existing systems for simulation-based language understanding and comprehension-driven grammar learning to represent, interpret and acquire a variety of contextually grounded construction.
  • Keywords
    computational linguistics; grammars; embodied construction grammar; grammar learning; language acquisition; language understanding; sensorimotor representations; simulation; structured context model; Computational modeling; Computer science; Concrete; Context modeling; Electrocardiography; Grounding; Robot sensing systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2006. IJCNN '06. International Joint Conference on
  • Conference_Location
    Vancouver, BC
  • Print_ISBN
    0-7803-9490-9
  • Type

    conf

  • DOI
    10.1109/IJCNN.2006.246625
  • Filename
    1716298