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...

We present a cognitive computational model of pronoun resolution that reproduces the human interpretation preferences of the Subject Assignment Strategy and the Parallel Function Strategy. Our model relies on a probabilistic pronoun resolution system trained on corpus data. Factors influencing pronoun resolution are represented as features weighted by their relative importance. The importance t...

We present an automatic approach to determining whether a pronoun in text refers to a preceding noun phrase or is instead nonreferential. We extract the surrounding textual context of the pronoun and gather, from a large corpus, the distribution of words that occur within that context. We learn to reliably classify these distributions as representing either referential or non-referential pronou...

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...

This paper presents an empirical evaluation of a pronoun resolution algorithm augmented with discourse segmentation information. Past work has shown that segmenting discourse can aid in pronoun resolution by making potentially erroneous candidates inaccessible to a pronoun’s search. However, implementing this in practice has been difficult given the complexities associated with deciding on a us...

Malay diri þ pronoun appears on initial examination to be a counter example to the typological claims made in the literature regarding the properties of long distance (LD) reflexives. It has been claimed that (1) LD reflexives are monomorphemic; (2) LD reflexives are subject oriented; (3) in languages without subject–verb agreement, LD reflexives manifest the Blocking Effect, the blocking of a ...

A memory-based processing approach to discourse comprehension emphasizes the rapid deployment of information in memory to facilitate understanding of the text that is currently being read. S. B. Greene, R. J. Gerrig, G. McKoon, and R. Ratcliff (1994) demonstrated that when a text described the reunion of 2 characters who had previously discussed a 3rd character, the accessibility of the 3rd cha...

The referent of a nonreflexive pronoun depends on context, but the nature of these contextual restrictions is controversial. For instance, in causal dependent clauses, the preferred referent of a pronoun varies systematically with the verb in the main clause (Sally frightens Mary because she … vs. Sally loves Mary because she …). Several theories claim that verbs with similar meanings across la...

We report the results of an experiment investigating the ramifications of using space to express coreference in American Sign Language (ASL). Nominals in ASL can be associated with locations in signing space, and pronouns are directed toward those locations to convey coreference. A probe recognition technique was used to investigate the case of "locus doubling" in which a single referent is ass...

This paper examines the automatic and strategic use of gender information in pronominal processing. Experiments 1 and 2 used short sentences where a pronoun was preceded by two potential antecedents. Results showed that even when adult readers did not use pronominal gender to strategically accelerate pronominal resolution, they remained sensitive to a gender disagreement between the pronoun and...