Mathematical Linguistics
Online ISSN : 2433-0302
Print ISSN : 0453-4611
Current issue
Showing 1-5 articles out of 5 articles from the selected issue
Paper (A)
  • Yohei Ono, Ryozo Yoshino, Fumi Hayashi, John Whitman
    Type: Paper (A)
    2017 Volume 31 Issue 3 Pages 189-204
    Published: December 20, 2017
    Released: January 11, 2019
    JOURNALS OPEN ACCESS
    This paper uses Multiple Correspondence Analysis (MCA) to re-analyze the linguistic data studied in Tsunoda, Ueda, and Itoh (1995a). Tsunoda et al. (1995a) applied cluster analyses to the word order parameters in Tsunoda, Ueda, and Itoh’s (1995b) database and identified as the main component the word order parameter category "prepositional," thus positing a basic dichotomy between prepositional languages versus adpositionless and postpositional languages. We reanalyze the same data using MCA, together with certain clustering techniques, applied to both the languages and the linguistic parameters in Tsunoda et al.’s (1995b) database simultaneously. This approach confirms the significance of word order parameters involving adposition but suggests a reconsideration of Tsunoda et al.’s (1995a) classification. We find a dichotomy between a cluster of "head-initial" (prepositional, verb-object, and noun-genitive) parameter categories versus a cluster of “head-final” (postpositional, object-verb, and genitive-noun) parameter categories similar to those often grouped together by linguists on the basis of informal cross-linguistic observations. We also find that Noun Phrase internal word order parameters, excepting parameter governing the order of noun and genitive, cluster separately from the others.
    Download PDF (2829K)
  • Hideaki Mori
    Type: Paper (A)
    2017 Volume 31 Issue 3 Pages 205-221
    Published: December 20, 2017
    Released: January 11, 2019
    JOURNALS OPEN ACCESS
    If any differences are found in the usage rate of a word between two corpora, the common method to verify them is to conduct a chi-square test using word frequencies. However, when an assumed word is used as an observation unit, there is criticism that it does not to meet the assumption of randomness underlying the statistical test. Basically, the choice of words and their regularity depends on the author’s judgment. In comparing the usage rate of a word, texts that reflect the author’s judgement, rather than the individual words should be observed as the observation units. In this paper, we propose an analytical method using a text as the observation unit to compare the usage rate of a word between two corpora. Differences of the usage rate of a word can be explained by the differences in the text frequency distribution. Furthermore, using text frequencies to perform a chi-square test makes it possible to effectively demonstrate the degree to which the text distribution varies between two corpora based upon their effect size. In comparing the usage rate of a word, therefore, we should consider the text rather than the word as an observation unit.
    Download PDF (1333K)
Book Review
Tutorial
feedback
Top