Disambiguation of the neuter pronoun and its effect on pronominal coreference resolution
Veronique Hoste, Iris Hendrikx and Walter Daelemans
In: Text, Speech and Dialogue: Proceedings of the 10th International Conference TSD 2007 Lecture Notes in Computer Science (4629). (2007) Springer Verlag , Berlin , pp. 48-55.

Abstract

Coreference resolution, determining the appropriate discourse referent for an anaphoric expression, is an essential but difficult task in natural language processing. It has been observed that an important source of errors in machine-learning based approaches to this task, is the wrong disambiguation of the third person singular neuter pronoun as ei- ther referential or non-referential. In this paper, we investigate whether a machine learning based approach can be successfully applied to the disambiguation of the neuter pronoun in Dutch and show a modest po- tential effect of this disambiguation on the results of a machine learning based coreference resolution system for Dutch.

[Edit]