Lodie,Web Scale Information Extraction via Linked Open Data

The World Wide Web provides access to tens of billions of pages. These pages contain information that is largely unstructured and only intended for human readability, however we are reliant on computers "reading" these pages in order to find the information we need. The proposed research intends to develop technologies to radically improve the billions of searches which are performed every day by fulfilling the initial vision, by Tim Berners-Lee, for a Web where the webpage content is readable by both humans and machines. Such a vision, disregarded during the initial development of the Web, has now come back in the form of the Web of Data, or Linked Open Data (LOD), where billions of pieces of information are linked together and made available for automated processing. There is however a lack of interconnection between the information in the webpages and that in LOD. A number of initiatives, like RDFa (supported by W3C) or Microformats (used by schema.org and supported by major search engines) are trying to enable machines to make sense of the information contained in human readable pages by providing the ability to annotate webpage content with links into LOD.
While the current state of the art in Web Information Extraction (IE) relies on domain specific training data or generic extraction patterns, by leveraging LOD the proposed research aims to develop IE methodologies and technologies providing pervasive, user-driven, Web-scale information extraction where the target of the IE is defined by the user information needs and aimed at the billions of available Web documents covering an unlimited number of domains.
In this research we aim to develop models and algorithms to create a continuum between LOD and the human readable Web. The approach will utilise wealth of facts available from LOD and the limited number of pages annotated with RDFa/Microformats to learn to connect unannotated webpage content to the LOD cloud. This will provide the reciprocal advantages of: (i) enabling the search of Web pages via the unambiguous LOD instances and concepts, and (ii) the extension of the LOD with the wealth of information available from webpage content.
The key challenge is the development of efficient, Web-scale, semi-supervised, iterative learning methods able to use the initial "seed" data and annotations, by generating models which exploit: (i) the local and global information regularities (e.g. structured information in tables, as well as pages and site-wide regularities); (ii) the redundancy (or repetition) of information; (iii) any ontological restrictions available in LOD. As the learning methods iterate from known interconnections to infer new connections they must cope with the massive amount of noise generated by the number and variety of documents, domains and facts available.
In addition to publishing the research and its findings the IE methods developed will be tested on the task of extracting information relevant to schema.org (a task currently promoted by large search engines companies such as Google and Bing) as well as in international public evaluations. As part of such evaluations the project will generate at least one publicly available, Web-scale IE task (inclusive of corpora, linked resources, etc.) to enable comparison of research results by other researchers.
The project aims to impact the fields of Natural Language Processing, Machine Learning, Information Retrieval and Web and Semantic Technologies by exploring the extraction of information in Web-scale, user-driven tasks. Success in the project will enable new ways of both creating/using the LOD and providing a paradigm shift in the way information can be retrieved from the Web; away from a reliance on keywords and towards the search and exploration of the concepts and meaning (semantics) embedded in those words.

Potential beneficiaries of the project results are technology, data and service providers as well as government and citizens.

IE tools providers
The project will advance the state of the art in Information Extraction from Web documents making it working at Web scale and portable with minimum user effort. Currently most companies are focussing on limited scale, on intensive porting effort or on very generic tasks such as named entities recognition (e.g. www.opencalais.com, www.ontotext.com). The project will enable going beyond these limitations. We will both generate know-how and tools published using a free licence such as MIT, which allows unlimited scientific and commercial reuse. These companies will benefit in a short-term scale, already during the lifetime of the project and through follow up knowledge transfer projects (e.g. via TSB or industrially funded projects).

Providers of information-based services
The use of LOD is one focus of research of the main search engines, as attested by the recent launch (May 2011) of schema.org. Schema.org focuses on their immediate needs by (i) asking users to manually annotate their pages and (ii) limiting the annotations to a set of specific domains which are the main core of the search engine business (e.g. eCommerce). The proposed project will enable search engines both not to depend on user's availability to annotate their pages and to go beyond the domain limitations in schema.org and to extend to the coverage of the whole LOD. We will provide input both in terms of know how and open source software.
Similarly, companies mining the social web (e.g. Twitter) for e.g. emergency responses and homeland security (e.g. k-now.co.uk), as well as companies providing specific services on the Web (e.g. price comparison sites) will be able to go beyond the current techniques that mainly require manual development of extraction methods. The technology developed will provide them with tools able to efficiently and effectively adapt to their needs, tasks and domains using the wealth of information available on the LOD. These organisations will benefit both during and after the lifetime of the project and through follow up knowledge transfer projects.

Data publishers
One of the main bottlenecks in publishing data is consistency analysis. While some publishers just dump their data as is and expect others to link and clean it, careful (esp. professional) publishers mind about the correctness and consistency of data, as well as their coverage. The project will provide measures of consistency and variability for data analysis and methods to integrate existing data with new data extracted form the Web. Data cleaning tools implementing the consistency measures will be available for use during the project lifetime. For other more complex applications, follow up knowledge transfer projects will be organised.

Government and society
IE has applications in - among others - homeland security, military applications, counter-terrorism and emergency response. The ability to identify events and facts over large scale has shown benefits in all those areas. The Web is a huge - largely untapped - source of information. As the proposed project will address the identification of facts and events over large scale, it will contribute to a safer society.

Web users and citizens
Finally consumers and citizens will benefit from the results of the project in an indirect way through the availability of new services based on large availability of interlinked data. One of the most prominent will be the improved search experience - with large quantity of quality data integrated onto the LOD, information search on the LOD can benefit in terms of both accuracy and coverage. The time frame for this is 1-5 years after the project end, when products based on the developed technology will have been industrialised and its benefits brought to the consumers.