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

Simple item page
dc.creatorSeki, Kazuhiro
dc.creatorFujii, Atsushi
dc.creatorIshikawa, Tetsuya
dc.date2002-06-20
dc.date.accessioned2026-07-07T03:18:32Z
dc.date.available2026-07-07T03:18:32Z
dc.descriptionThis 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.
dc.descriptionProceedings of the 19th International Conference on Computational Linguistics (To appear)
dc.identifierhttps://arxiv.org/abs/cs/0206030
dc.identifierhttp://arxiv.org/abs/cs/0206030
dc.identifierProceedings of the 19th International Conference on Computational Linguistics (COLING 2002), pp.911-917, Aug. 2002
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31152
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleA Probabilistic Method for Analyzing Japanese Anaphora Integrating Zero Pronoun Detection and Resolution
dc.typetext

Files

Collections

arXiv