A Probabilistic Method for Analyzing Japanese Anaphora Integrating Zero Pronoun Detection and Resolution

TL;DR

This paper introduces a probabilistic approach that simultaneously detects zero pronouns and resolves their antecedents in Japanese, improving analysis of omitted obligatory cases in discourse.

Contribution

It presents a unified probabilistic framework for zero pronoun detection and resolution, integrating two parameters and utilizing annotated corpora for efficient computation.

Findings

Effective zero pronoun detection demonstrated

Improved antecedent resolution accuracy

Method outperforms previous approaches

Abstract

This paper proposes a method to analyze Japanese anaphora, in which zero pronouns (omitted obligatory cases) are used to refer to preceding entities (antecedents). Unlike the case of general coreference resolution, zero pronouns have to be detected prior to resolution because they are not expressed in discourse. Our method integrates two probability parameters to perform zero pronoun detection and resolution in a single framework. The first parameter quantifies the degree to which a given case is a zero pronoun. The second parameter quantifies the degree to which a given entity is the antecedent for a detected zero pronoun. To compute these parameters efficiently, we use corpora with/without annotations of anaphoric relations. We show the effectiveness of our method by way of experiments.