The Japanese Translation Task: Lexical and Structural Perspectives
Timothy J. Baldwin, Atsushi Okazaki, Takenobu Tokunaga, Hozumi Tanaka · 2001
This paper describes two distinct attempts at the Senseval2 Japanese translation task. The first implementation is based on lexical similarity and builds on the results of Baldwin (2001b; 2001a), whereas the second is based on structural similarity via the medium of parse trees and includes a basic model of conceptual similarity. Despite its simplistic nature, the lexical method was found to perform the better of the two, at 49.1% accuracy, as compared to 41.2% for the structural method and 36.8% for the baseline. 1