Extraction of time-related expressions using text mining with application to Hebrew‏

Dror Mughaz, Yaakov HaCohen-Kerner, Gabbay Dov

Abstract:

In this research, we extract time-related expressions from a rabbinic text in a semi-automatic
manner. These expressions usually appear next to rabbinic references (name / nickname /
acronym / book-name). The first step toward our goal is to find all the expressions near references in the corpus. However, not all of the phrases around the references are time-related
expressions. Therefore, these phrases are initially considered to be potential time-related
expressions. To extract the time-related expressions, we formulate two new statistical functions, and we use screening and heuristic methods. We tested these statistical functions,
grammatical screenings, and heuristic methods on a corpus containing responsa documents. In this corpus, many rabbinic citations are known and marked. The statistical functions and the screening methods filtered the potential time-related expressions and reduced
99.88% of the initial expressions (from 484,681 to 575).