This paper proposes a method to extract rules for anaphora resolution of Japanese zero pronouns from aligned sentence pairs. The method focuses on the characteristics of Japanese and English in which both the language families and the distribution of zero pronouns are very different. In this method, zero pronouns in the Japanese sentence and the English translation equivalents of their antecede...

The present paper discusses two interesting phenomena concerning phifeatures on plural pronouns: (i) plural pronouns that denote atomic individuals (‘dependent plural pronouns’), and (ii) plural pronouns with more than one binder (‘partial binding’). A novel account of these two phenomena is proposed, according towhich all occurrences of phi-features are both semantically and morphologically re...

This paper presents a new study on the distribution, identification, and resolution of zero pronouns in Romanian. A Romanian corpus, including legal, encyclopaedic, literary, and news texts has been created and manually annotated for zero pronouns. Using a morphological parser for Romanian and machine learning methods, experiments were performed on the created corpus for the identification and ...

Certain properties of indefinite pronouns have received considerable attention in the literature. For instance, negative polarity indefinites such as English any constitute the focus of the bulk of the literature on negative polarity items, the fact notwithstanding that Klima in his seminal 1964 paper did not fail to show that members of other syntactic and semantic categories may be restricted...

The term anaphora describes backward reference to items previously occurring in a text (see e.g., Mitkov, 2002). The pointing back item is called an anaphor and the item to which it refers is called its antecedent. The identification of an anaphor’s antecedent is termed anaphora resolution and is considered one of the most difficult tasks in natural language processing (NLP) since it relies on ...

kakhki dialect is one of the dialects of the south of razavi khorasan province which is spoken in a subdivision of gonabad, called “kakhk”. this dialect and two other dialects (khaniki and ferdowsi), as far as the researcher knows, are the only linguistically described dialects in the razavi khorasan and south khorasan provinces which have the ergative case marking. ergative case marking in thi...

In two experiments, we examined the recent claim (Stewart, Pickering, & Sanford, 2000) that verb-based implicit causality information is used during sentence–final clausal integration only. We did so by looking for mid-sentence reading delays caused by pronouns that are inconsistent with the bias of a preceding implicit causality verb (e.g., ‘‘David praised Linda because he. . .’’). In a self-p...

Pronouns without explicit noun phrase antecedents pose a problem for any theory of reference resolution. We report here on an empirical study of such pronouns in the Santa Barbara Corpus of Spoken American English, a corpus of spontaneous, casual conversation. Analysis of 2,046 third person personal pronouns in fourteen transcripts indicates that 330 (or 16.1%) lack NP antecedents. These pronou...

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...