Abstract
Coreference is usually defined as phenomenon consisting in different expressions relating to the same referent. Therefore automatic coreference resolution is an extremely difficult and complex task. It can be approached in two different ways: using rule-based tools or machine learning. This article is dedicated to the second approach and describes an evaluation of a set of surface, syntactic, discourse, salience and anaphoric features proposed by Uryupina and their usefulness for coreference resolution in Polish texts.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have