Justifying Corpus-Based Choices in Referring Expression Generation
Helmut Horacek · Recent Advances in Natural Language Processing · 2013
Most empirically-based approaches to NL generation elaborate on co-occurrences and frequencies observed over a corpus, which are then accommodated by learning algorithms. This method fails to capture generalities in generation subtasks, such as generating referring expressions, so that results obtained for some corpus cannot be transferred with confidence to similar environments or even to other domains. In order to obtain a more general basis for choices in referring expression generation, we formulate situational and task-specific properties, and we test to what degree they hold in a specific corpus. As a novelty, we incorporate features of the role of the underlying task, object identification, into these property specifications; these features are inherently domain-independent. Our method has the potential to enable the development of a repertoire of regularities that express generalities and differences across situations and domains, which supports the development of generic algorithms and also leads to a better understanding of underlying dependencies.