Since January 2009 I’ve been working at True Knowledge, a Cambridge startup. My work there centers on data-mining, web-crawling, entity disambiguation and natural language processing.

My PhD aims to augment the Geographic Information Retrieval process with information extracted from world knowledge. This aim is approached from three directions: classifying world knowledge, disambiguating placenames and modelling users. Geographic information is becoming ubiquitous across the Internet with a significant proportion of web documents and web searches containing geographic entities, and the proliferation of internet enabled mobile devices. Traditional information retrieval treats these geographic entities in the same way as any other textual data. I augment the retrieval process with geographic information and show that methods built upon world knowledge outperform methods based on heuristic rules.

I employ Wikipedia as source of world knowledge. Wikipedia has become a phenomenon of the internet age and needs little introduction. As a linked corpus of semi-structured data, it is unsurpassed. Two approaches to mining information from Wikipedia are rigorously explored: initially I classify Wikipedia articles into broad categories; this is followed by much finer classification where Wikipedia articles are disambiguated as specific locations. My thesis concludes with the proposal of the Steinberg hypothesis. By analysing a range of wikipedias in different languages I demonstrate that a fish-eye localised view of the world is ubiquitous and inherently part of human nature.

The core contributions of my work are in the areas of extracting information from Wikipedia, supervised placename disambiguation, and providing a quantitative model for how people view the world. The findings clearly have a direct impact for applications such as geographically aware search engines, but in a broader context documents can be automatically annotated with machine readable meta-data and dialogue can be enhanced with a model of how people view the world. This could potentially reduce ambiguity and confusion in dialogue between people or computers.

Over the summer of 2007 I took an interuption of studies to complete part of my research as an intern at Yahoo! Research Barcelona. To test your system against my geographically tagged set of Wikipedia pages please download my ground truth. Please contact me if you would like any help or achieve any results. The data generated in our most recent co-occurrence model has now been released. This data and more is now viewable on a map and available via an API.