Neural Network-based Chinese Joint Syntactic Analysis

ニューラルネットワークに基づく係り受け解析モデルは,近年の深層学習を利用した言 語処理研究の中でも大きな潮流となっている.しかしながら,こうした係り受け解析モ デルを中国語などの言語に適用した際には,パイプラインモデルとして同時に用いられ る単語分割や品詞タグ付けモデルの無視できない誤りによって性能が伸び悩む問題が 存在する.これに対しては,単語分割・品詞タグ付けと係り受け解析の統合モデルを利 用し,単語分割と構文木作成とを同時に行うことでその双方の改善が期待される.加え て,中国語においては個々の文字が固有の意味を持ち,構文解析では,文字やその組み 合わせである文字列もしくは部分単語の情報が単語単位の情報と並んで本質的な役割を 果たすことが期待される.本研究では,ニューラルネットワークに基づいて,単語分割 と品詞タグ付け,もしくは単語分割と品詞タグ付け,係り受け解析の統合構文解析を行 うモデルを提案する.また,同時に,文字列や部分単語の情報を捉えるために,文字や 単語の分散表現に加えて,文字列の分散表現を利用する. キーワード:構文解析,係り受け解析,遷移に基づく解析,深層学習,単語の分散表現

[1]  Eliyahu Kiperwasser,et al.  Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations , 2016, TACL.

[2]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Slav Petrov,et al.  Globally Normalized Transition-Based Neural Networks , 2016, ACL.

[5]  Stephen Clark,et al.  A Fast Decoder for Joint Word Segmentation and POS-Tagging Using a Single Discriminative Model , 2010, EMNLP.

[6]  Slav Petrov,et al.  Structured Training for Neural Network Transition-Based Parsing , 2015, ACL.

[7]  Slav Petrov,et al.  Improved Transition-Based Parsing and Tagging with Neural Networks , 2015, EMNLP.

[8]  Geoffrey E. Hinton,et al.  Learning distributed representations of concepts. , 1989 .

[9]  Kenji Sagae,et al.  Dynamic Programming for Linear-Time Incremental Parsing , 2010, ACL.

[10]  Jun'ichi Tsujii,et al.  Incremental Joint POS Tagging and Dependency Parsing in Chinese , 2011, IJCNLP.

[11]  Daisuke Kawahara,et al.  Chinese Word Segmentation and Unknown Word Extraction by Mining Maximized Substring , 2016 .

[12]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[13]  Yoshimasa Tsuruoka,et al.  Improving Chinese Word Segmentation and POS Tagging with Semi-supervised Methods Using Large Auto-Analyzed Data , 2011, IJCNLP.

[14]  Yue Zhang,et al.  Character-Level Chinese Dependency Parsing , 2014, ACL.

[15]  Noah A. Smith,et al.  Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs , 2015, EMNLP.

[16]  Yue Zhang,et al.  A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing , 2015, ACL.

[17]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[18]  Qun Liu,et al.  A Cascaded Linear Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging , 2008, ACL.

[19]  Chenhui Chu,et al.  Consistent Word Segmentation, Part-of-Speech Tagging and Dependency Labelling Annotation for Chinese Language , 2016, COLING.

[20]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[21]  James Cross,et al.  Incremental Parsing with Minimal Features Using Bi-Directional LSTM , 2016, ACL.

[22]  Joakim Nivre,et al.  Incrementality in Deterministic Dependency Parsing , 2004 .

[23]  Noah A. Smith,et al.  Transition-Based Dependency Parsing with Stack Long Short-Term Memory , 2015, ACL.

[24]  Regina Barzilay,et al.  Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing , 2015, HLT-NAACL.

[25]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[26]  Stephen Clark,et al.  A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing , 2008, EMNLP.

[27]  Jun'ichi Tsujii,et al.  Incremental Joint Approach to Word Segmentation, POS Tagging, and Dependency Parsing in Chinese , 2012, ACL.

[28]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.