Neural Network-Based Model for Japanese Predicate Argument Structure Analysis

This paper presents a novel model for Japanese predicate argument structure (PAS) analysis based on a neural network framework. Japanese PAS analysis is challenging due to the tangled characteristics of the Japanese language, such as case disappearance and argument omission. To unravel this problem, we learn selectional preferences from a large raw corpus, and incorporate them into a SOTA PAS analysis model, which considers the consistency of all PASs in a given sentence. We demonstrate that the proposed PAS analysis model significantly outperforms the base SOTA system.

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

[2]  Yoshimasa Tsuruoka,et al.  Jointly Learning Word Representations and Composition Functions Using Predicate-Argument Structures , 2014, EMNLP.

[3]  Hiroyuki Shindo,et al.  Joint Case Argument Identification for Japanese Predicate Argument Structure Analysis , 2015, ACL.

[4]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[5]  Ivan Titov,et al.  Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework , 2014, NAACL.

[6]  Yuji Matsumoto,et al.  Japanese Predicate Argument Structure Analysis Exploiting Argument Position and Type , 2011, IJCNLP.

[7]  Daisuke Kawahara,et al.  Japanese Zero Reference Resolution Considering Exophora and Author/Reader Mentions , 2013, EMNLP.

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

[9]  Masaaki Nagata,et al.  A Japanese Predicate Argument Structure Analysis using Decision Lists , 2008, EMNLP.

[10]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[11]  Tomoko Izumi,et al.  Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution , 2009, ACL.

[12]  Wei Xu,et al.  End-to-end learning of semantic role labeling using recurrent neural networks , 2015, ACL.

[13]  Daisuke Kawahara,et al.  Building a Diverse Document Leads Corpus Annotated with Semantic Relations , 2012, PACLIC.

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

[15]  Sadao Kurohashi,et al.  A Discriminative Approach to Japanese Zero Anaphora Resolution with Large-scale Lexicalized Case Frames , 2011, IJCNLP.

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

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

[18]  Regina Barzilay,et al.  Greed is Good if Randomized: New Inference for Dependency Parsing , 2014, EMNLP.

[19]  Jong-Hoon Oh,et al.  Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition , 2015, EMNLP.

[20]  Ben Taskar,et al.  Learning structured prediction models: a large margin approach , 2005, ICML.