A Discriminative Approach to Japanese Abbreviation Extraction
Naoaki Okazaki, Mitsuru Ishizuka, Jun’ichi Tsujii · 2008
This paper addresses the difficulties in recognizing Japanese abbreviations through the use of previous approaches, examining actual usages of parenthetical expressions in newspaper articles. In order to bridge the gap between Japanese abbreviations and their full forms, we present a discriminative approach to abbreviation recognition. More specifically, we formalize the abbreviation recognition task as a binary classification problem in which a classifier determines a positive (abbreviation) or negative (nonabbreviation) class, given a candidate of abbreviation definition. The proposed method achieved 95.7 % accuracy, 90.0 % precision, and 87.6 % recall on the evaluation corpus containing 7,887 (1,430 abbreviations and 6,457 non-abbreviation) instances of parenthetical expressions. 1