Analysis of the Effect of Dependency Information on Predicate-Argument Structure Analysis and Zero Anaphora Resolution

2017/05/31 by Koichiro Yoshino, Yoshino, Koichiro, Shinsuke Mori +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1705.10962

arxiv created 2017/05/31 · openalex publication_date 2017/05/31 · arxiv updated 2017/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper investigates and analyzes the effect of dependency information on predicate-argument structure analysis (PASA) and zero anaphora resolution (ZAR) for Japanese, and shows that a straightforward approach of PASA and ZAR works effectively even if dependency information was not available. We constructed an analyzer that directly predicts relationships of predicates and arguments with their semantic roles from a POS-tagged corpus. The features of the system are designed to compensate for the absence of syntactic information by using features used in dependency parsing as a reference. We also constructed analyzers that use the oracle dependency and the real dependency parsing results, and compared with the system that does not use any syntactic information to verify that the improvement provided by dependencies is not crucial.

Related

• Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
• Hierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification
• Multi-task Learning for Japanese Predicate Argument Structure Analysis
• Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis
• Distance-Free Modeling of Multi-Predicate Interactions in End-to-End Japanese Predicate-Argument Structure Analysis