Our taxonomy experts have broad experience in both large academic-type taxonomies and smaller, more functional business taxonomies. In addition, unlike taxonomists whose only experience is slow and laborious hand development, our taxonomy experts have significant experience using our text analytics tools, making them much more effective taxonomists.

Taxonomy Customization
The KAPS Group can take existing taxonomies, whether from an external source or your own internal development and transform them into text analytics resources. To do this often requires a major restructuring into smaller and more flexible structures that more accurately reflect how users think and how they search for information.

One common technique that often works well is to turn a broad taxonomy into set of facets or a faceted taxonomy. We do this in part by an analysis of an existing taxonomy looking for common elements that show up in multiple places in the taxonomy, such as methods or functions. We also use entity or noun phrase extraction to fully populate candidate facets such as locations, people, or organizations.

The KAPS Group has extensive experience in text analytics of all kinds and with most text analytics vendors. We offer development services for building a text analytics foundation as well as adding text analytics to specific applications such as search or sentiment analysis.

We can quickly develop entity catalogs of such entities as people, places, companies as well as more custom entity types such as method. These entity catalogs can be used as a stand alone resource or as part of a taxonomy or ontology.
We also have experience with developing advanced automatic summarization of sets of documents. These summaries can be simple summaries of the top few ideas in a document or complex summaries of whole sets of documents that capture and present all the significant information in those documents.

The real heart (or mind) of text analytics is its "auto-categorization" capability where the software is used to categorize the "aboutness" of a document using either statistical or rules-based categorization. Even though they are often sold separately, software for sentiment analysis uses these same techniques. However, these "auto-categorization" capabilities can be used for much more than simple categorization. They can add depth and intelligence to all of the other text analytics capabilities and applications from e-Discovery to business intelligence to customer support to (anything that does or can use text in one way or another).

This is where the Deep Text approach of the KAPS Group is particularly effective and valuable. We have experience in everything from enhancing traditional applications to using text analytics for creative new applications.

  Knowledge Management Development

KM has traditionally been leery of information technology based initiatives and too often those did produce something that did not capture the depth and richness of knowledge. However, text analytics done with a Deep Text approach can capture and utilize knowledge in all its richness.
The KAPS Group has developed a set of methods that start with creating a text analytics foundation that can model the meaning found within documents and use that meaning to enrich KM applications like communities of practice and expertise location. This can be done within a single KM initiative or could be the creation of an enterprise KM capability that supports all existing KM applications and is flexible enough to be expanded to new KM initiatives.