We propose an unsupervised probabilistic model for zero pronoun resolution. To our knowledge, this is the first such model that (1) is trained on zero pronouns in an unsupervised manner; (2) jointly identifies and resolves anaphoric zero pronouns; and (3) exploits discourse information provided by a salience model. Experiments demonstrate that our unsupervised model significantly outperforms it...

In this paper, we present a machine learning approach to the identification and resolution of Chinese anaphoric zero pronouns. We perform both identification and resolution automatically, with two sets of easily computable features. Experimental results show that our proposed learning approach achieves anaphoric zero pronoun resolution accuracy comparable to a previous state-ofthe-art, heuristi...

The basic concepts in Centering Theory, such as utterance, ranking and R1-pronouns, are purposely left unspecified to concrete tasks. The proper setting of these parameters in Chinese anaphoric resolution is examined in this study. Six resolution algorithms are designed to examine the effectiveness of the instantiations of different parametric settings. The results reveal that utterances, when ...

In Japanese, particularly, spoken Japanese, subjective, objective and possessive cases are very often omitted. Such Japanese sentences are often translated by Japanese-English statistical machine translation to the English sentence whose subjective, objective and possessive cases are omitted, and it causes to decrease the quality of translation. We performed experiments of J-E phrase based tran...

This paper describes a method for automatic acquisition of wide-coverage treebank-based deep linguistic resources for Japanese, as part of a project on treebankbased induction of multilingual resources in the framework of Lexical-Functional Grammar (LFG). We automatically annotate LFG f-structure functional equations (i.e. labelled dependencies) to the Kyoto Text Corpus version 4.0 (KTC4) (Kuro...

Abstract Coreference processing of Control constructions and their pronoun-containing counterparts can be studied experimentally using priming or interference paradigms. We replicate findings in a study on non-finite Norwegian (Larsen & Johansson, 2020) contrast them with finite effects grammatical maze (G-maze) design. asked participants to read sentences word-by-word select the grammatica...

The ultimate aim of the following pages is to explore the hypothesis that sentences containing a pronoun be analyzed as involving a topic pronoun doubling relation in a way that closely parallels the one overtly realized in Clitic Left Dislocation (CLLD) and Hanging Topic (HT) structures in Italian/Romance. In a nutshell: when a pronoun is present in the clause, a silent doubled non-overt topic...

This paper explores how to apply the notion of caching introduced by Walker (1996) to the task of zero-anaphora resolution. We propose a machine learning-based implementation of a cache model to reduce the computational cost of identifying an antecedent. Our empirical evaluation with Japanese newspaper articles shows that the number of candidate antecedents for each zero-pronoun can be dramatic...

Existing approaches for Chinese zero pronoun resolution typically utilize only syntactical and lexical features while ignoring semantic information. The fundamental reason is that zero pronouns have no descriptive information, which brings difficulty in explicitly capturing their semantic similarities with antecedents. Meanwhile, representing zero pronouns is challenging since they are merely g...