Mining Neologisms from a Large Diachronic Web Archive for Supporting Linguistic Research
Nobuhiro Kaji, Ryoko Uno, Masaru Kitsuregawa · 2009
Neologisms have been an object of study in linguistics. However, because of the lack of linguistic resources, it has been difficult for linguists to investigate neologisms. To resolve this situation, we are investigating to make use of a Web archive (e.g. the Internet Archive) for such linguistic research. Because we can find plenty of neologisms on the Web, a Web archive is an unquestionably valuable resource for the linguistics community. This paper reports our attempt to support linguistic analysis of neologisms based on a large Web archive. We also show our initial results on linguistic analysis of neologisms using a time-series Web archive.