Seed Selection for Distantly Supervised Web-Based Relation Extraction
Isabelle Augenstein · 2014
In this paper we consider the problem of distant supervision to extract relations (e.g. origin(musical artist, location)) for entities (e.g. ‘The Beatles’) of certain classes (e.g. musical artist) from Web pages by using background information from the Linking Open Data cloud to automatically label Web documents which are then used as training data for relation classifiers. Distant supervision approaches typically suffer from the problem of ambiguity when automatically labelling text, as well as the problem of incompleteness of background data to judge whether a mention is a true relation mention. This paper explores the hypothesis that simple statistical methods based on background data can help to filter unreliable training data and thus improve the precision of relation extractors. Experiments on a Web corpus show that an error reduction of 35 % can be achieved by strategically selecting seed data. 1