Japanese Dependency Analysis using a Deterministic Finite State Transducer

A deterministic finite state transducer is a fast device for analyzing strings. It takes O(n) time to analyze a string of length n. In this paper, an application of this technique to Japanese dependency analysis will be described. We achieved the speed at a small cost in accuracy. It takes about 0.17 millisecond to analyze one sentence (average length is 10 bunsetsu, based on PentiumIII 650MHz PC, Linux) and we actually observed the analysis time to be proportional to the sentence length. The accuracy is about 81% even though very little lexical information is used. This is about 17% and 9% better than the default and a simple system, respectively. We believe the gap between our performance and the best current performance on the same task, about 7%, can be filled by introducing lexical or semantic information.

• Type: Conference
• Year: 2000
• Where: COLING
• Authors: Satoshi Sekine
• Keywords: COLING 2000, COLING 2008, Deterministic Finite State, Japanese Dependency Analysis, Pentiumiii 650mhz Pc