I recently attended a tribute to Karen Spärck Jones at The Royal Society of Medicine hosted by the British Computer Society. It was breath taking to listen to Dr Ann Copestake a Reader in Computational Linguistics in the Computer Laboratory, University of Cambridge.
Her lecture on tackling some of the issues relating semantic representation and processing was breathtaking and intense. Ann’s lecture covered discussions on scientific text processing and how this relates to semantic web publishing to that of Karen Spärck Jones’s concept of the ‘Information Layer’, who was one of the pioneering academic in information retrieval and natural language processing.
This was abit hard to digest and took me a while to make connections with what interaction designers and web developers are doing at the moment. Only when I stumbled across Powerset did I realise the true extent of what I’d come across. Searching for information on the web can be quiet frustrating if you don’t know exactly the correct keywords to use. Google does a pretty good job but it can still do better in making it easier for users to find the correct information needed.
Say you’re searching on Google to learn about paintings by Salvador Dali. In comparison Google searches will return thousands of results, which you will have to go to the individual web pages to see if they’re what you want. If they are, you then have to search through those pages for the information you want. If you want to know about a particular painting but can’t remember the name of the painting, the search could quickly become frustrating. A search for paintings by Salvador Dali will be helpful, but it requires some effort to hunt through the results.
Instead Powerset’s technology currently at beta stage, promises to provide sets of results based either on entire web pages (currently done by Google) or on specific sections of those pages, which is helpful if they’re extensive Wikipedia entries. I think the company’s ambitions are towards reading through pages for you and arranging or condensing the information it finds to just tell you an answer tailored to your search.
This is a huge task and also interesting to see that people are not just relying on just images as an alternative to searching for content online but are looking at language semantics as the main focus in truly perfecting how we retrieve information online.