Naslov
Exploring Coreference Uncertainty of Generically Extracted Event Mentions

Autori
Glavaš, Goran ; Šnajder, Jan

Izvornik
Lecture Notes in Computer Science ; Computational Linguistics and Intelligent Text Processing (0302-9743) 7816 (2013); 408-422

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
event extraction; coreference resolution

Sažetak
Because event mentions in text may be referentially ambiguous, event coreferentiality often involves uncertainty. In this paper we consider event coreference uncertainty and explore how it is affected by the context. We develop a supervised event coreference resolution model based on the comparison of generically extracted event mentions. We analyse event coreference uncertainty in both human annotations and predictions of the model, and in both within- document and cross-document setting. We frame event coreference as a classification task when full context is available and no uncertainty is involved, and a regression task in a limited context setting that involves uncertainty. We show how a rich set of features based on argument comparison can be utilized in both settings. Experimental results on English data suggest that our approach is especially suitable for resolving cross-document event coreference. Results also suggest that modelling human coreference uncertainty in the case of limited context is feasible.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA