Information retrieval is the science of searching for (and finding) information relevant to a user need. The most common, most visible application of information retrieval science is found in modern web search engines, though the roots of the field extend decades before the web sprung into existence and encompass wider varieties of information needs than are typically found on the web.
The continued evolution of the field was on full display during the recent 41st European Conference on Information Retrieval (ECIR), held April 14-18 in Cologne, Germany. ECIR, which is now in its fifth decade, is a major get-together of leading information retrieval (IR) experts and data scientists from academia as well as companies including Microsoft, Google, Salesforce, IBM and others.
In addition to three main conference days in which scientists present their peer-reviewed work to conference attendees, this year’s ECIR included an Industry Day that focused on applied IR technology. OpenText’s Dr. Jeremy Pickens presented a talk titled “E-Discovery and Internal Investigations: The Forgotten Frontiers of Information Retrieval.” In it, he made the argument that four common challenges that lawyers face have more in common with historical IR tasks than with modern web tasks.
Specifically, he identified challenges that lawyers face, the solutions to which are not simply to find a single factoid or navigate to a single document, but to find an entire set of documents that collectively paint a picture: Discovery, Narrative Extraction, Internal Investigations, and Legal Entailment. These four areas can roughly be described as (a) finding all (or proportionally all) documents responsive to a matter, (b) finding the probative documents that support your narrative, and simultaneously prevent your opponent from supporting a counter-narrative, (c) finding documents before they become a problem, and (d) finding existing case law onto which one’s current matter may be projected.
Dr. Pickens then related these tasks to historical IR problem spaces, and challenged the research community to return its attention to these historical, but as-yet not completely solved areas. His insights into the application of IR to solve complicated e-discovery and investigations problems earned him the ECIR Industry Day Best Presentation award.