SWAT: A System for Detecting Salient Wikipedia Entities in Texts
This work addresses entity salience detection for applications in natural language processing, but it appears incremental as it builds on existing methods with improvements in performance.
The authors tackled the problem of identifying salient Wikipedia entities in text by developing SWAT, a system that uses supervised learning on syntactic, semantic, and latent features trained on millions of examples from the New York Times corpus, and it improves over known solutions across all publicly available datasets.
We study the problem of entity salience by proposing the design and implementation of SWAT, a system that identifies the salient Wikipedia entities occurring in an input document. SWAT consists of several modules that are able to detect and classify on-the-fly Wikipedia entities as salient or not, based on a large number of syntactic, semantic and latent features properly extracted via a supervised process which has been trained over millions of examples drawn from the New York Times corpus. The validation process is performed through a large experimental assessment, eventually showing that SWAT improves known solutions over all publicly available datasets. We release SWAT via an API that we describe and comment in the paper in order to ease its use in other software.