PolyUHK: A Robust Information Extraction System for Web Personal Names

Personal information extraction is an important component of advanced information retrieval. There are two problems needed to be solved in this practical task: personal name ambiguity and extraction of personal information for a specific person. For personal name ambiguity, which is a very common phenomenon in the fast growing Web resource, we propose a robust system which extracts features with a totally unsupervised approach from resources beyond the given Web corpus. The experiments show that these broad features not only can improve performances, but also increase the robustness of a disambiguation system. For personal information extraction, a rule-based information extraction system is introduced, which is able to re-use current well-developed tools effectively and identify the properties of Web data. The experiments show that the system can achieve state-of-the-art performances, especially the high precision.