I have been thrilled with the response and interest in my last post referring to Pandia’s top five semantic search engines. It is a topic that I find fascinating and apparently lots of other people do too. I have had some interesting email exchanges with lawyers and programmers on the topic since I posted on Tuesday and have learned a great deal more than I knew two days ago.

I want to share with you a few highlights. First, I was contacted by Dmitri Soubbotin at SenseBot. Mr. Soubbotin is a senior manager there and will be speaking at the upcoming Boston Search Engine Meeting in April, 2009. There is a highly informative interview with Mr. Soubbotin here, at Beyond Search from ArnoldIT.com, a blog about search and content processing. Mr. Soubbotin was interested in hearing how lawyers could employ semantic search, i.e. what kinds of documents or uses might be envisioned. We agreed that there were unstructured documents that lawyers might be interested in accessing that would be ripe for the special “semantic” overlay that enables relevance-based searching. We talked about scientific and medical research, intellectual property information, internal compliance documentation, large-scale discovery materials (searching for privileged documents based on relevance could be very helpful in the course of litigation), people and asset information and other generalized web-documents. I should also point out that semantic search could be quite valuable within the enterprise intranet for organizing the scores of documents that even small and mid-sized businesses produce.

I would love to get feedback from the legal readership here as to how they might use a semantic web tool in their practice or marketing efforts.

I also received an email from Lee Gesmer at the Boston firm of Gesmer Updegrove, LLP. In 2005, partner Andrew Updegrove had interviewed Tim Berners-Lee, the father of the World Wide Web and champion of the Semantic Web movement. The link here is the ten page interview, with Berners-Lee’s comments about how the Semantic Web works and where it fits in the evolutionary process. I read the interview with great interest – although it is three years old, the information Mr. Berners-Lee provides still seems new and exciting. It is a great primer for anyone wanting to understand how the Semantic Web works and what the W3C is trying to effect. Mr. Gesmer also provided a link to ConsortiumInfo.org, a site maintained by Mr. Updegrove offering information about standards, standard setting and open source software.The firm provides legal representation to consortia and open source foundations and has amassed quite a collection of information furthering these efforts.

I have learned much from my simple act of blogging about Semantic Search engines. The flow of relevant information back and forth between citizens of the Web: isn’t this what the evolution of the Web to its 3.0 version is all about?