|
The dbi technologies inc. xAIgent is an agnostic content summarization technology that automatically parses news, information, documents... into relevant and contextually accurate abbreviated summaries.
Uniquely positioned as a restful service implementation of the Extractor key phrase extraction technology (www.extractor.com), xAIgent can be immediately deployed consuming documents of any length and subject matter and distilling that information into precise, contextual, personally meaningful information presented in keyword and key phrase summaries. The xAIgent’s unique patented technology delivers precise content summaries from any subject domain automatically - without training - without human intervention.
Contextual
A unique feature of the xAIgent technology is the ability to summarize content by showing how keywords and key phrases are used in context of a document allowing for accurate definition of terminology and use of the subject. Resulting summaries provide unparalleled levels of subject relevance. Analyzing collections of documents with contextual relevance is now possible.
Relevant Information
By design the xAIgent is an objective provider of content summaries in contrast to traditional human influenced subjective summary approaches or approximated systems using Bayesian and Heuristic approaches. Statistically proven, the patented technology used in the xAIgent is 85% to 93% accurate across all subject domains.The ability to quickly discern relevant and meaningful news and information - in personal context - is the corner stone of the xAIgent process.
Definition of Key Phrase Extraction
Many journals ask their authors to provide a list of key words for their articles. We call these key phrases, rather than key words, because they are often phrases of two or more words, rather than single words. A key phrase list is defined as a short list of phrases (typically five to fifteen phrases) that capture the main topics discussed in a given document. Automatic key phrase extraction is defined as the automatic selection of important, topical phrases from within the body of a document. Automatic key phrase extraction is a special case of the more general task of automatic key phrase generation, in which the generated phrases do not necessarily appear in the body of the given document.
Key Phrases for Metadata
Many researchers believe that metadata is essential to address the problems of document management. Metadata is meta-information about a document or set of documents. There are several standards for document metadata, including the Dublin Core Metadata Element Set (championed by the US Online Computer Library Center), the MARC (Machine-Readable Cataloging) format (maintained by the US Library of Congress), the GILS (Government Information Locator Service) standard (from the US Office of Social and Economic Data Analysis), and the CSDGM (Content Standards for Digital Geospatial Metadata) standard (from the US Federal Geographic Data Committee). All of these standards include a field for key phrases (although they have different names for this field).
Key Phrases for Highlighting
When we skim a document, we scan for key phrases, to quickly determine the topic of the document. Highlighting is the practice of emphasizing key phrases and key passages (e.g., sentences or paragraphs) by underlining the key text, using a special font, or marking the key text with a special colour. The purpose of highlighting is to facilitate skimming. Automatic key phrase extraction can be used for highlighting and also to enable text-to-speech software to provide audio skimming capability.
Key Phrases for Indexing
An alphabetical list of key phrases, taken from a collection of documents or from parts of a single long document (chapters in a book), can serve as an index.
Key Phrases for Interactive Query Refinement
Using a search engine is often an iterative process. The user enters a query, examines the resulting hit list, and modifies the query, then tries again. Most search engines do not have any special features that support the iterative aspect of searching. One approach to interactive query refinement is to take the user's query, fetch the first round of documents, extract key phrases from them, and then display the first round of documents to the user, along with suggested refinements to the first query, based on combinations of the first query with the extracted key phrases.
Key Phrases for Web Log Analysis
Web site managers often want to know what visitors to their site are seeking. Most web servers have log files that record information about visitors, including the Internet address of the client machine, the file that was requested by the client, and the date and time of the request. There are several commercial products that analyze these logs for web site managers. Typically these tools will give a summary of general traffic patterns and produce an ordered list of the most popular files on the web site. A web log analysis program can use key phrases to provide a deeper view of traffic. Instead of producing an ordered list of the most popular files on the web site, a log analysis tool can produce a list of the most popular key phrases on the site. This can give web site managers insight into which topics on their web site are most popular.
Workforce Optimization
Relevant information is a critical tool for the success of any business today and providing relevant information in the right context is what gives an organization an ultimate competitive advantage. Rather than working through traditional, time consuming, iterative search processes - engage the Text Mining power of Extractor to empower information workers with relevant and meaningful results in direct relation to their needs and those of today's dynamic workforce.
|