OrcaTec LLC

The OrcaTec Information Discovery Toolkit for Web 2.0 and Beyond

The OrcaTec Information Discovery Toolkit is a suite of tools for analyzing, searching, and discovering electronic text information. Most of the tools are based on language modeling.
Click here to download this paper.

Concept search without the FUD

Concept search has been receiving increasing attention from legal professionals and the courts. Despite many years of use, a lot of misunderstanding still seems to be prevalent about what concept search is and what it does. There is a lot of unnecessary fear, uncertainty, and doubt about concept search, which this paper seeks to dispel.

Download the paper here

Hashing, identity, and duplication in eDiscovery

This paper addresses questions regarding using hash functions in electronic discovery.
Recent developments in research on hashing functions, particularly the MD5 hash function, have led some people in eDiscovery to wonder about their continued use. These concerns are addressed in this paper.
Download the paper here.

Trends in eDiscovery 2008

We identify three trends in the evolution of electronic discovery for 2008. These trends are the product of Judicial decisions, the continued explosion in the volume of electronically stored information and the recently revised Federal Rules of Civil Procedure.
Download the paper here

Evidence-based Search Evaluation

In this paper, we consider the evaluation of search efficacy from a practical perspective. The “proof” of the adequacy of a search, indeed of an entire review process, is in the documents that were retrieved. The main expertise that is required to evaluate search is to ensure that this evaluation is done fairly, accurately, and inexpensively. Download the paper here.