• DocumentCode
    3195579
  • Title

    Combining finite state automata and a greedy learning algorithm to determine the syntactic roles of commas

  • Author

    Van Delden, Sebastian ; Gomez, Fernando

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Central Florida, Orlando, FL, USA
  • fYear
    2002
  • fDate
    2002
  • Firstpage
    293
  • Lastpage
    300
  • Abstract
    A method has been developed and implemented that assigns syntactic roles to commas. Text that has been tagged using a part-of-speech tagger serves as the input to the system. A set of Finite State Automata first assigns temporary syntactic roles to each comma in the sentence. A greedy learning algorithm is then used to determine the final syntactic roles of the commas. The system requires no training and is not domain specific. The performance of the system on numerous corpora is given.
  • Keywords
    computational linguistics; finite state machines; learning (artificial intelligence); natural languages; finite state automata; greedy learning; natural languages; part-of-speech tagger; syntactic roles; syntactic roles of commas; Learning automata; NASA; Natural languages; Speech; Tagging;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings. 14th IEEE International Conference on
  • ISSN
    1082-3409
  • Print_ISBN
    0-7695-1849-4
  • Type

    conf

  • DOI
    10.1109/TAI.2002.1180817
  • Filename
    1180817