Search results for: simple

Searching for a single term within a document is pretty black or white. It is either present or not. When you step up to searching based on phrases, proximity terms, concepts and compound term clusters things start to get a bit less absolute. Yet, simple lists of terms are generally either overly broad or are missing relevant ESI. The simplest search index does not store information about the position(s) of terms within a document. Modern search indexes such as Lucene, FAST, IDOL and others rely on term position and other information to derive clusters of two or more related terms (concepts) and relevance weighting factors. During a recent briefing call with Mike Wade, CTO of Planet Data, we delved into some of the challenges that Planet Data faced expanding their Exego Early Cost Assessment platform to support concept search and ECA workflow. What really caught my attention was the ability to extract two separate versions of the text from documents, both the raw unformatted text AND the rendered view. Alternatively, they have developed a merged rendering that embeds the extracted object text in-line with the viewed text.

Legal Tech NY 2011 is less than a week away. It just so happens that we launched eDJ at LTNY 2010, so we have been working hard on some new tools. We have completely rewritten my old eDiscovery Application Matrix and transformed it into the eDJ Tech Matrix. The most noticeable immediate change is our new capability to compare individual applications or features across entire company offerings. The eDiscovery market is still relatively young and it is dominated by start-ups with a single software offering. However, we have seen acquisitions by global technology companies such as Autonomy, EMC, Iron Mountain and IBM. That means you might want to see how an individual product compares AND then see all the features offered by a company. Up till this point, the roughly 100 applications in the Tech Matrix had been submitted exclusively by users and the providers.

In some ways I feel like I missed out on parts of Legal Tech NY 2011. My focus this year was to fit in as many roadmap briefings as possible. The sheer scale and audience focus of LTNY has forced providers to plan major product releases and announcements around the show. Product managers would ask me, “Didn’t you see our press release?” Even if I saw it, there were so many in the eDJ search queue that I could not remember them all. So instead of keynotes, sessions, panels or even the exhibition floor, I spent virtually all of my time hearing about the very latest products, features and where the providers think that eDisovery is going this year. With so many briefings, I am going to stick to short summaries and high points. There were quite a few providers who did not have a coherent message or any new functionality significant enough to mention. On with the fun.

Continuing my high level take-aways from my roadmap briefings at LegalTech NY 2011. Predictive coding was one of the hot topics at this show, but it seemed to mean something different to every provider. There is enough confusion around the issue to merit a solid research topic for eDJ in the upcoming months. I know that The eDiscovery Institute is looking to do a comparative research project on predictive coding in 2011-2012, so we can look forward to some hard numbers going into next year from them. On to the provider updates:

As we head into “LegalTech season,” I would normally expect some hyperbole around not-so-well defined terms like “ECA” or “the cloud.” And while there is certain to be some marketing hype around the show, it feels like this year will feature more pragmatism. I expect to see more messaging around actual benefits that solutions have delivered and less “generic” messaging about how many additional features a platform or service has implemented.

A client recently asked me what kinds of themes will dominate this year’s Legal Tech show. In an earlier post, Expectations for LegalTech 2011, I pointed out some of what I think we’ll see at the show, but what I didn’t do in the last post was address what I think will be the overall theme in 2001 – a focus on the practice of eDiscovery. Yes, I believe we are now actually moving up the maturity curve and discussions will focus on real issues and how real solutions to problems. There will still be a lot of hype around issues du jour, but that hype will take a back seat to the very real case studies that many companies are now willing to talk about.

I recently finished a research paper that takes an overview of Enterprise Search for Discovery. My intent was to aggregate, organize and condense corporate client discussions around this area over the last year. Enterprise search and preservation collection platforms are the second most frequent technology RFP engagement for my corporate clients after archiving systems. The technology providers have many different approaches, architectures and features that can confuse the prospective buyer. After having the same discussion so many times, I decided to put together a low cost ($29) overview report to at least define the options, potential benefits, costs and things to consider before investing in enterprise search. Enterprise search tends to fall into two main indexing camps, selective vs. enterprise wide. One element from the report is the potential index size, as indexes like to live on Tier 1 class storage (SAN, Direct Attached or other top class storage).

One of the challenges in the eDiscovery market is the need for organizations to keep best practices to themselves. There are few organizations willing to publicly share the details of eDiscovery programs. True, one of the reasons for this is the fact that most eDiscovery programs are very immature. But, the primary reason is risk control – there is very little benefit to going public with eDiscovery practices and a lot of downside (e.g. losing the ability to argue undue burden because the whole world knows about your search capabilities). Thus, I was very happy when I found someone from a top telecomm company willing to share some lessons learned (while I can’t share name or company name, I can share some very interesting knowledge nuggets)

After watching the IBM Watson debut on Jeopardy, I got to thinking more and more about computer intelligence. I’ve been watching the content analytics space for a long time and have seen up close both the potential for analytics to change the world and the skepticism with which many humans view analytics. When I began covering eDiscovery, it seemed to me that there was finally a market in which content analytics could make a real impact and find some traction. This is especially true in Early Case Assessment (ECA).

At the IPRO Innovations 2011 customer conference in Phoenix last week, I participated in an excellent panel discussion focused on the potential impact of large enterprise ECM and archiving platforms expanding into the eDiscovery lifecycle. Panelists Ronald Sotak of Ryley Carlock & Applewhite and Olivia Gerroll of Esentio brought excellent if divergent perspectives. The first thing to realize is that the majority of our audience consisted of IPRO channel partners, i.e. eDiscovery service providers. Some service providers are threatened by global software companies’ recent push to incorporate eDiscovery features into enterprise platforms. Specialty markets like eDiscovery can be eroded when their services are absorbed into normal corporate business processes. So the real question was, “Will in-house software platforms replace the vendors?”