A Predictive Model for Notional Anaphora in English
This work addresses a specific problem in natural language processing for coreference resolution and referring expression generation, but it is incremental as it builds on existing data and methods.
The paper tackled the challenge of predicting notional anaphora in English, such as plural pronouns with singular antecedents, by using an ensemble approach on the OntoNotes corpus, achieving state-of-the-art prediction accuracy and revealing that factors at the anaphor's utterance and genre strongly influence expression choice.
Notional anaphors are pronouns which disagree with their antecedents' grammatical categories for notional reasons, such as plural to singular agreement in: 'the government ... they'. Since such cases are rare and conflict with evidence from strictly agreeing cases ('the government ... it'), they present a substantial challenge to both coreference resolution and referring expression generation. Using the OntoNotes corpus, this paper takes an ensemble approach to predicting English notional anaphora in context on the basis of the largest empirical data to date. In addition to state of the art prediction accuracy, the results suggest that theoretical approaches positing a plural construal at the antecedent's utterance are insufficient, and that circumstances at the anaphor's utterance location, as well as global factors such as genre, have a strong effect on the choice of referring expression.