Impact of Coreference Resolution on Slot Filling

TL;DR

This paper investigates how coreference resolution affects slot filling tasks, demonstrating its importance and providing experimental evidence of performance improvements, along with a new resource for researchers.

Contribution

It highlights the impact of coreference resolution on slot filling and introduces KBPchains, a resource of automatically extracted coreference chains for research support.

Findings

Coreference resolution improves slot filling performance.

Automatic coreference systems have notable strengths and weaknesses.

KBPchains aids future research in coreference and slot filling.

Abstract

In this paper, we demonstrate the importance of coreference resolution for natural language processing on the example of the TAC Slot Filling shared task. We illustrate the strengths and weaknesses of automatic coreference resolution systems and provide experimental results to show that they improve performance in the slot filling end-to-end setting. Finally, we publish KBPchains, a resource containing automatically extracted coreference chains from the TAC source corpus in order to support other researchers working on this topic.