Content Enabler is a linguistic API for those companies that want to further the re-use of knowledge. Content Enabler provides powerful data sets that help users to build the most meaningful queries, which will in turn lead to finding more relevant documents. It allows users to search their knowledge repositories intelligently using their own language, regardless of the language or the word use of the documents to be searched. Apart from many European languages, Content Enabler also supports industry- and company-specific thesauri.
The problem with finding relevant existing information is the process of constructing a meaningful query.
Typically, when a user has thought of a query, he doesn’t fully realise what the intricacies of language do to that query. If, in the user’s mind, the query is concise, in language terms it may be unclear or even arbitrary. The richness of the phenomenon language can easily confuse search systems with multiple meanings in one language and even more so across boundaries of different languages. Refining the query to contain conceptual meanings and clear and concise expressions is the challenge that Content Enabler helps you meet.
Another issue adding to the frustration of an irritatingly large hit list is industry~ or company specific terminology. This can largely be solved by integrating that terminology into Content Enabler.
To construct a clear and concise query takes a lot of time. Since most users don’t allow time for this effort, they are ‘rewarded’ by having to spend a lot of time in sorting through the hit list. One way or another, the user will have to spend time, either in building a good query or in sifting through the hit list.
Content Enabler helps users to easily construct a relevant and meaningful query, clear and concise. To successfully do this, you can pick and choose from a number of datasets that can be applied to the content of your intranet.
The available datasets are:
· Semantic networks (also known as word nets) - for the following languages: Dutch, English, German, French, Spanish and Italian. These networks can be used in monolingual as well as cross-lingual environments. They enable the automatic query and index enhancement.
· Industry or company specific thesauri – these thesauri cover the word meanings recurring in language that is being used in a certain domain. All available thesauri are ISO compliant.
· Gazetteers and authority files – these are proper name files that form a natural complement to semantic networks and thesauri. Gazetteers provide a hierarchical overview of for instance geographic names while authority files contain the proper names of currencies, languages, people and/or organizations.
The use of Content Enabler means that users spend less time constructing meaningful queries, enabling the existing search engine to return more relevant hits.
The user saves time and avoids frustration on both sides of the process – in query building and in sorting through the hit list. While saving time he is also capable of making better supported decisions.
Content Enabler can be easily integrated with existing search engines and/or document management systems. An overview of technical specifications can be sent to you upon request.
Existing integrations are available with Convera RetrievalWare, FAST ESP and Open Text LiveLink.
|
