RESLVE: Leveraging User Interest to Improve Entity Disambiguation on Short Text
It addresses ambiguity in social media posts for users and platforms, but appears incremental as it builds on existing NED methods with a user-interest model.
The paper tackled the Named Entity Disambiguation problem for short, user-generated texts on social media, where conventional systems suffer from a 50% accuracy drop, and achieved substantial performance gains beyond state-of-the-art methods.
We address the Named Entity Disambiguation (NED) problem for short, user-generated texts on the social Web. In such settings, the lack of linguistic features and sparse lexical context result in a high degree of ambiguity and sharp performance drops of nearly 50% in the accuracy of conventional NED systems. We handle these challenges by developing a model of user-interest with respect to a personal knowledge context; and Wikipedia, a particularly well-established and reliable knowledge base, is used to instantiate the procedure. We conduct systematic evaluations using individuals' posts from Twitter, YouTube, and Flickr and demonstrate that our novel technique is able to achieve substantial performance gains beyond state-of-the-art NED methods.