Imagine you are taking an introductory biology course. You’re studying for an exam and realize it would be helpful to revisit the professor’s explanation of RNA interference. Fortunately for you, a digital recording of the lecture is online, but the 10-minute explanation you want is buried in a 90-minute lecture you don’t have time to watch.

A new lecture search engine developed at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) could help with this dilemma. Created by a team of researchers and students led by MIT associate professor Regina Barzilay and principal research scientist James Glass, the web-based technology allows users to search hundreds of MIT lectures for key topics.

More than 200 MIT lectures are currently available on the site. So far, most of the users are international students who access the lectures through MIT’s OpenCourseWare (OCW) initiative, which makes curriculum materials for most MIT courses available to anyone with Internet access.

Many MIT professors record their lectures and post them online, but it’s difficult to search them for specific topics. Because there is no way to easily scan audio, as you can with printed text, “you end up watching the whole thing, and it’s hard to keep focused,” said Barzilay, the Douglas T. Ross Career Development Associate Professor of Software Development in the Department of Electrical Engineering and Computer Science.

On the prototype web site, users can search lectures for any term they want and then play the relevant sections.  (See what happens when I search for ’search engines’)

The lecture transcripts are created by speech recognition software. One major challenge is that the lectures usually contain many technical terms that might not be in the computer program’s vocabulary, so the researchers use textbooks, lecture notes and abstracts to identify key terms and feed them into the computer.  When properly adapted to a speaker and topic, the lecture-based speech recognizer gets about four out of five words correct, however most of the errors occur in words that are not critical to the lecture topic, i.e., not the key vocabulary terms that people would use to search.

In the future, Barzilay and Glass hope to add a lecture summarization feature to the language processing system. They also want to get users more involved in the project, by incorporating a Wikipedia-like function that would let users correct errors in lecture transcripts and allow them to add lecture notes.

Thanks to Federico for this great tip!

This entry was posted on Thursday, November 15th, 2007 at 1:23 pm and is filed under Reviews. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.