This paper investigates the problem of Chinese zero pronoun resolution. Most existing approaches are based on machine learning algorithms, using hand-crafted features, which is labor-intensive. Moreover, semantic information that is essential in the resolution of noun phrases has not been addressed enough by previous approaches on zero pronoun resolution. This is because that zero pronouns have...

This paper argues for the necessity of zero pronoun annotations in Korean treebanks and provides an annotation scheme that can be used to develop a gold standard for testing different anaphor resolution algorithms. Relevant issues of pronoun annotation will be discussed by comparing the Penn Korean Treebank with zero pronoun mark-up and the newly developing Sejong Teebank without zero pronoun m...

In Korean, in order to generate a coherent text, a redundantly prominent noun should be replaced by a non-zero pronoun or zero pronoun. Otherwise, the text becomes unnatural. Specifically, a redundant noun in Korean is frequently omitted while a redundant noun in English is replaced by a pronoun. This paper proposes a generation algorithm of the zero pronoun, using a Cost-based Centering Model ...

Masked language models (MLMs) have contributed to drastic performance improvements with regard zero anaphora resolution (ZAR). To further improve this approach, in study, we made two proposals. The first is a new pretraining task that trains MLMs on anaphoric relations explicit supervision, and the second proposal finetuning method remedies notorious issue, pretrain-finetune discrepancy. Our ex...

We extend Zhao and Ng's (2007) Chinese anaphoric zero pronoun resolver by (1) using a richer set of features and (2) exploiting the coreference links between zero pronouns during resolution. Results on OntoNotes show that our approach significantly outperforms two state-of-the-art anaphoric zero pronoun resolvers. To our knowledge, this is the first work to report results obtained by an end-toe...

State-of-the-art Chinese zero pronoun resolution systems are supervised, thus relying on training data containing manually resolved zero pronouns. To eliminate the reliance on annotated data, we present a generative model for unsupervised Chinese zero pronoun resolution. At the core of our model is a novel hypothesis: a probabilistic pronoun resolver trained on overt pronouns in an unsupervised...

This paper proposes a statistical zero pronoun resolution method that utilizes features of verbs. In Japanese speech, the subject is often omitted, especially when it is the first person. To resolve such zero pronouns, features related to the verbs such as functional expressions play important roles. However, recent state-of-the-art zero-pronoun resolution systems lack these features because th...

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 ...

The aim of this paper is to report the distribution of Spanish zero pronouns in three different genres: legal, encyclopaedic and instructional. The Z-corpora were created for this purpose and a sample of 1043 zero pronouns was annotated. The most salient patterns of distribution are compared for each genre, and some relevant issues concerning the use of zero pronouns are described in relation t...

This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in ...