论文信息 - A Unified Single Scan Algorithm for Japanese Base Phrase Chunking and Dependency Parsing

A Unified Single Scan Algorithm for Japanese Base Phrase Chunking and Dependency Parsing

We describe an algorithm for Japanese analysis that does both base phrase chunking and dependency parsing simultaneously in linear-time with a single scan of a sentence. In this paper, we show a pseudo code of the algorithm and evaluate its performance empirically on the Kyoto University Corpus. Experimental results show that the proposed algorithm with the voted perceptron yields reasonably good accuracy.

Sadao Kurohashi | Manabu Sassano

[1] Hitoshi Isahara,et al. Japanese Dependency Structure Analysis Based on Maximum Entropy Models , 1999, EACL.

[2] Yoav Freund,et al. Large Margin Classification Using the Perceptron Algorithm , 1998, COLT' 98.

[3] Hitoshi Isahara,et al. Backward Beam Search Algorithm for Dependency Analysis of Japanese , 2000, COLING.

[4] Masafumi Nishimura,et al. A Stochastic Parser Based on a Structural Word Prediction Model , 2000, COLING.

[5] Makoto Nagao,et al. Building a Japanese parsed corpus while improving the parsing system , 1997 .

[6] Shinsuke Mori. A Stochastic Parser Based on an SLM with Arboreal Context Trees , 2002, COLING.

[7] Ulrich H.-G. Kreßel,et al. Pairwise classification and support vector machines , 1999 .

[8] Yuji Matsumoto,et al. Japanese Dependency Analysis using Cascaded Chunking , 2002, CoNLL.

[9] Manabu Sassano,et al. Linear-Time Dependency Analysis for Japanese , 2004, COLING.

[10] Sabine Buchholz,et al. CoNLL-X Shared Task on Multilingual Dependency Parsing , 2006, CoNLL.