Kalina Bontcheva, University of Sheffield
The Semantic Web aims to add a machine tractable, re-purposeable layer to compliment the existing web of natural language hypertext. In order to realise this vision, the creation of semantic annotation, the linking of web pages to ontologies, and the creation, evolution and interrelation of ontologies must become automatic or semi-automatic processes.
The web revolution so far has been based largely on human language materials, and in making the shift to the next generation knowledge-based web, human language will remain key. Human Language Technology involves the analysis, mining and production of natural language. HLT has matured over the last decade to a point at which robust and scaleable applications are possible in a variety of areas, and new actions in the Semantic Web domain are now poised to exploit this development. The included graph illustrates the way in which Human Language Technology can be used to bring together the natural language upon which the current web is mainly based and the formal knowledge at the basis of next generation Semantic Web.
Information Extraction (IE) is a process which takes unseen texts as input and produces fixed-format, unambiguous data as output. This data may be used directly for display to users, or may be stored in a database or spreadsheet for later analysis, or may be used for indexing purposes in Information Retrieval (IR) applications.
It is instructive to compare IE and IR:
Whereas IR simply finds texts and presents them to the user, the typical IE application analyses texts and presents only the specific information from them that the user is interested in. For example, a user of an IR system wanting information on the share price movements of companies with holdings in Bolivian raw materials would typically type in a list of relevant words and receive in return a set of documents (e.g. newspaper articles) which contain likely matches. The user would then read the documents and extract the requisite information themselves. They might then enter the information in a spreadsheet and produce a chart for a report or presentation.
In contrast, an IE system user could, with a properly configured application, automatically populate their spreadsheet directly with the names of companies and the price movements.
The new challenge for IE is to populate ontologies and generate metadata. Natural Language Generation (NLG) is the inverse of IE: from structured data in a knowledge base NLG techniques produce natural language text, tailored to the presentational context and the target reader. NLG techniques use and build models of the context and the user and use them to select appropriate presentation strategies. For example, deliver short summaries to the user's WAP phone or a longer multimodal text if the user is using their desktop. Similarly, NLG techniques can use simpler terminology and explain unknown terms to the naive user, while different terminology and text style is used for the expert user. The new challenge for NLG is to generate texts from ontologies and metadata, which requires the development of new NLG methods allowing easy portability between domains, based on machine learning.
Further reading:
A description of the use of metadata and associated issues (from Ontotext)
http://www.ontotext.com/kim/semanticannotation.html
An up-to-date presentation of examples of technologies for metadata generation, also from Ontotext.
(While the first describes a commercial product, the second is an open-source research tool.)
http://www.ontotext.com/kim/introduction.html
and
http://www.gate.ac.uk/projects/sekt/
CLOSE WINDOW TO EXIT
|
