• Login
    View Item 
    •   Athenaeum Home
    • University of Georgia Theses and Dissertations
    • University of Georgia Theses and Dissertations
    • View Item
    •   Athenaeum Home
    • University of Georgia Theses and Dissertations
    • University of Georgia Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    SYCORAX

    Thumbnail
    Date
    2011-08
    Author
    Boisclair, William Cody
    Metadata
    Show full item record
    Abstract
    This dissertation describes the development and evaluation of a new analyzer for syntactic complexity known as SYCORAX: the SYntactic COmplexity RAting eXpert. SYCORAX, like several prior applications for automated analysis of syntactic complexity (e.g., Long et al., 2006; Channell, 2007; MacWhinney, 2011), is based on the Developmental Sentence Scoring (DSS) scale developed by Lee (1974). These existing applications, however, all have one significant limitation in common: they are all strictly based on immediate linear context within a sentence. It is evident from prior work (Channell, 2003; Judson, 2006) that certain syntactic structures involved in DSS are simply not apparent from linear context alone; indeed, many structures incorrectly analyzed by human raters are due to incorrect interpretation of local context (Lively, 1984). In contrast, SYCORAX incorporates a newly-developed shallow dependency parser known as JED (Just Enough Dependency) optimized for the dependencies which are important in DSS, and uses the resulting parse tree in the calculation of its DSS scores. Even without complete optimization of its DSS rules, the use of shallow parsing in SYCORAX produces a distinct overall boost in the accuracy of syntactic complexity scores on a variety of manually-scored real-world transcripts, as measured using Pearson correlation coefficient and point-by-point accuracy, with no significant increase in execution time. DSS has proven numerous times to be psycholinguistically valid. It was originally designed to identify language delays in children, and more recent experiments have found it to still be valid in that respect (e.g., Scarborough, 1990); in addition, it has been found to be of use in identifying language decline in adults (Cheung and Kemper, 1992; Kemper et al., 2003, 2004), distinguishing different forms of developmental delay (Finestack and Abbeduto, 2010), and even identifying Alzheimer’s dementia (Kemper et al., 1993). It is believed that the improvement in its automated analysis by SYCORAX will prompt even further research regarding it, much as the prior project CPIDR (Brown et al., 2008) has done for semantic complexity (Covington et al., 2009; Jarrold et al., 2010; Engelman et al., 2010; Tsai, 2010).
    URI
    http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd
    http://hdl.handle.net/10724/27392
    Collections
    • University of Georgia Theses and Dissertations

    About Athenaeum | Contact Us | Send Feedback
     

     

    Browse

    All of AthenaeumCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    About Athenaeum | Contact Us | Send Feedback