The Noisy Channel


E-Discovery and Transparency

September 1st, 2008 · 2 Comments · Uncategorized

One change I’m thinking of making to this blog is to introduce “quick bites” as a way of mentioning interesting sites or articles I’ve come across without going into deep analysis. Here’s a first one to give you a flavor of the concept. Let me know what you think.

I just read an article on how courts will tolerate search inaccuracies in e-Discovery by way of Curt Monash. It reminded me of our recent discussion of transparency in information retrieval. I agree that “explanations of [search] algorithms are of questionable value” for convincing a court of the relevance and accuracy of the results. But that’s because those algorithms aren’t sufficiently intuitive for those explanations to be meaningful except in a theoretical sense to an information retreival researcher.

I realize that user-entered Boolean queries (the traditional approach to e-Discovery) aren’t effective because users aren’t great at composing queries for set retrieval. But that’s why machines need to help users with query elaboration–a topic for an upcoming post.

2 responses so far ↓

  • 1 Anonymous // Sep 3, 2008 at 1:07 pm

    I like the change, but I also hope you keep the longer posts.

  • 2 Daniel Tunkelang // Sep 3, 2008 at 8:43 pm

    Thanks for the feedback. I’ll try to mix it up.

Clicky Web Analytics