This paper proposes a method to resolve Japanese zero pronouns by identifying their antecedents. Our method uses a probabilistic model, which is decomposed into syntactic and semantic properties. A syntactic model is trained based on corpora annotated with anaphoric relations. However, a semantic model is trained based on a large-scale unannotated corpus, so as to counter the data sparseness pr...

Binding constraints form one of the most robust modules of grammatical knowledge. Despite their crosslinguistic generality and practical relevance for anaphor resolution, they have resisted full integration into grammar processing. The ultimate reason for this is to be found in the original exhaustive coindexation rationale for their specification and verification. As an alternative, we propose...

We present a machine learning approach to identifying and resolving one-anaphora. In this approach, the system first learns to distinguish different uses of instances of the word one; in the second stage, the antecedents of those instances of one that are classified as anaphoric are then determined. We evaluated our approach on written texts drawn from the informative domains of the British Nat...

This paper sketches an approach to pronoun reference resolution in context based on a dynamic incremental semantics for NL in polymorphic type theory. Our set-up provides full incrementality of processing, and can handle salience and pronoun resolution in context. An implementation of the system in Haskell, in ‘literate programming’ style, exists. The full literate source code can be found at h...

Recent research suggests that pronoun interpretation is guided by the semantic coherence relations between clauses. However, it is not yet wellunderstood whether coherence effects extend to other anaphoric expressions beyond pronouns. We report an experiment on German, a language in which human antecedents can be referred to both with personal and demonstrative pronouns. How do anaphoric demons...

This paper presents a new model of anaphoric processing that utilizes the establishment of coherence relations between clauses in a discourse. We survey data that comprises a currently stalemated argument over whether VP-ellipsis is an inherently syntactic or inherently semantic phenomenon, and show that the data can be handled within a uniform discourse processing architecture. This architectu...

We report on experiments in reference resolution using a decision tree approach. We started with a standard feature set used in previous work, which led to moderate results. A closer examination of the performance of the features for different forms of anaphoric expressions showed good results for pronouns, moderate results for proper names, and poor results for definite noun phrases. We then i...

The Bayesian Network (BN) formalism has been scarcely used to model NLP problems. However this formalism has real advantages to overcome the limits of traditional knowledge-based approaches in NLP. Since anaphora resolution is a traditional problem in NLP, we propose a system based on a BN for the recognition of non-anaphoric occurences of the pronoun it and show that this formalism takes advan...

We present an unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within each document. While most existing coreference work is driven by pairwise decisions, our model is fully generative, producing each mention from a combination of global entity properties and local atten...

This paper presents an experimental study on the interpretation of plural pronoun they in discourse, and offers an answer to two questions. The first question is whether the anaphoric interpretation of they corresponds to that of its antecedent NP(maximal interpretation), or by the “whole” previous sentence (reference interpretation). The second question is whether speakers may access only one ...