It is more and more important to have tools that make the access to the huge quantity of information available through the Internet as well as through the organizations' internal information systems easier.
In Daedalus we have at our disposal the technology to process the information according to the following dimensions:
Format: the presence of videos and audio files in the Internet is more and more important and the search systems must find the way of understanding these multimedia contents, giving them a meaning for the user
Language: Internet, as well as its users, is by nature a multilingual environment. The search tools must be able to work with any language, giving to the users the opportunity of using at every moment the one that they find most appropriate
Structure: being able to analyze the morphological as well as syntactical and semantic language structures can make the difference in the quality of results of a search system
On the other hand, from the point of view of the consultation, we think at Daedalus that the users must have at their disposal tools expressing the searches that they are interested in and go beyond the text box in which some words are written. An alternative is the use of conversational agents built on Question Answering systems, capable of getting precise replies to answers instead of lots of links to websites. For example, if a user wants to know Barack Obama's year of birth through a general purpose search engine, he or she would use this type of phrase: 'birth Barack Obama' and get as a result a list of websites that he should look up one by one until finding the information that he is searching for. This user could also ask: 'What is Barack Obama's year of birth?' and get, through a Question Answering system, the exact answer '1961' and a link to the website from which the information was extracted. The user should also have the option of reading its consultation and not only writing it. This profound analysis of the websites content is object of study in the Information extraction technology, which is based on the information provided by the Semantic Web technology, capable of isolating the data linked to the presentation of the websites from their semantic content and giving them a meaning. At Daedalus we have at our disposal the technology needed to carry out these analyses in all the levels and adapt them to our clients' environment.
Besides, the Question Answering systems must always be on the alert for new information appearing in the Internet and that is why an auxiliary technology is needed, from robots capable of carrying out an automatic exploration of the information appearing in the Internet to tools capable of transforming formats.