Joint Event Detection and Entity Resolution: a Virtuous Cycle

TL;DR

This paper introduces a joint approach to event detection and entity resolution in web documents, leveraging a virtuous cycle where each task enhances the other, demonstrated on news article data.

Contribution

It proposes a novel method that simultaneously clusters news articles and resolves entity co-references, improving both tasks iteratively.

Findings

The joint method outperforms separate approaches in clustering accuracy.

Entity resolution benefits from clustering context, leading to more accurate co-reference.

The virtuous cycle enhances overall performance in event detection and entity resolution.

Abstract

Clustering web documents has numerous applications, such as aggregating news articles into meaningful events, detecting trends and hot topics on the Web, preserving diversity in search results, etc. At the same time, the importance of named entities and, in particular, the ability to recognize them and to solve the associated co-reference resolution problem are widely recognized as key enabling factors when mining, aggregating and comparing content on the Web. Instead of considering these two problems separately, we propose in this paper a method that tackles jointly the problem of clustering news articles into events and cross-document co-reference resolution of named entities. The co-occurrence of named entities in the same clusters is used as an additional signal to decide whether two referents should be merged into one entity. These refined entities can in turn be used as enhanced features to re-cluster the documents and then be refined again, entering into a virtuous cycle that improves simultaneously the performances of both tasks. We implemented a prototype system and report results using the TDT5 collection of news articles, demonstrating the potential of our approach.