January 9, 2013
Twitter’s use of actual humans to make sense of its search results, points to the mundane reality that even with machine learning and lots of data, sometimes humans are the best source for insights.
Check out twitter’s post http://tinyurl.com/ar6dqyw
As soon as twitter discovers a new popular search query, they send it to human evaluators on Amazon’s Mechanical Turk service, who are asked a variety of questions about the query. The feedback from humans is then fed to the machine learning models that will make use of the additional information
January 6, 2013
The organizational approach in enterprise content and records management systems has traditionally relied upon the use of document attribute data as the primary information source for content storage and retrieval. Attributes such as business units, document types, expiration dates, functional areas, and similar things are common.
In the past few years content and records management applications have often used a “facetted” taxonomy design to define how the content and/or records are classified.
Is this sufficient? It might be acceptable in some cases for content management, but falls short of expectations for knowledge management.
Large volumes of knowledge content are often well suited to auto-categorization. he tools and methods most commonly used for auto-categorization are text analytics or image analysis. This can be expensive to implement. This makes it challenging for small law offices to benefit from this technology, who also have large volumes of data to contend with.
In coming blogs, I will talk about how to deliver inexpensive solutions to the problem.
November 7, 2012
A lot of focus has been placed on delivering automated solutions with no human interaction. We however need to invest in more than just making machines smarter. We need to train our employees to become more sophisticated consumers of the outputs of their machines. Then, the network effect will begin to bringing more value out of data than ever before.
The biggest victories in the man-machine framework come when machine learning is appropriately delivered to respect the role of humans.
In the E-Discovery space, the better machine learning products actively learn from documents marked by human reviewers to produce continuously improved results expediting the review process