Background linking: Joining entity linking with learning to rank models

The recent years have been characterized by a strong democratization of news production on the web. In this scenario it is rare to find self-contained news articles that provide useful background and context information. The problem of finding information providing context to news articles has been tackled by the Background Linking task of the TREC News Track. In this paper, we propose a system to address the background linking task. Our system relies on LambdaMART learning to rank algorithm trained on classic textual features and on entity-based features. The idea is that the entities extracted from the documents as well as their relationships provide valuable context to the documents. We analyzed how this idea can be used to improve the effectiveness of (re-)ranking methods for the background linking task.