|
MIT develops lecture search engine to aid students
November 15, 2007Imagine 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 Laboratory (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.
"Our goal is to develop a speech and language technology that will help educators provide structure to these video recordings, so it's easier for students to access the material," said Glass, who is head of CSAIL's Spoken Language Systems Group.
More than 200 MIT lectures are currently available on the site (web.sls.csail.mit.edu/lectures/). 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. Although the lecture-browsing system is still in the early development stages, a recent announcement in OCW's newsletter has drawn increased traffic to the site.
Barzilay and Glass expect the system will be most useful for OCW users and for MIT students who want to review lecture material. MIT World, a web site that provides video of significant MIT events such as lectures by speakers from MIT and around the world, is also participating in the project.
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.
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.
"These lectures can have a very specialized vocabulary," said Glass. "For example, in an algebra class, the professor might talk about Eigenvalues."
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.
Once the transcript is complete, a language processing program divides the text into sections by topic. Chunks of text, about 100 words each, are compared with each other using a mathematical formula that calculates the number of overlapping words between the text blocks. Each word is weighted so that repetition of key terms has more weight than less important words, and chunks with the most similar words are grouped into sections.
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.
The researchers presented their project at the Interspeech 2007 conference in Antwerp, Belgium, in August. The project was originally funded by Microsoft through the iCampus program and is now funded by the National Science Foundation.
Massachusetts Institute of Technology
More than 200 MIT lectures are currently available on the site (web.sls.csail.mit.edu/lectures/). 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. Although the lecture-browsing system is still in the early development stages, a recent announcement in OCW's newsletter has drawn increased traffic to the site.
Barzilay and Glass expect the system will be most useful for OCW users and for MIT students who want to review lecture material. MIT World, a web site that provides video of significant MIT events such as lectures by speakers from MIT and around the world, is also participating in the project.
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.
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.
"These lectures can have a very specialized vocabulary," said Glass. "For example, in an algebra class, the professor might talk about Eigenvalues."
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.
Once the transcript is complete, a language processing program divides the text into sections by topic. Chunks of text, about 100 words each, are compared with each other using a mathematical formula that calculates the number of overlapping words between the text blocks. Each word is weighted so that repetition of key terms has more weight than less important words, and chunks with the most similar words are grouped into sections.
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.
The researchers presented their project at the Interspeech 2007 conference in Antwerp, Belgium, in August. The project was originally funded by Microsoft through the iCampus program and is now funded by the National Science Foundation.
Massachusetts Institute of Technology
Search Engine News and Current Search Engine Events RSSScientists launch first comprehensive database of human oral microbiome
Scientists know more today than ever before about the microbes that inhabit our mouths. They know so much, in fact, that gathering all of the relevant bits of information into one place when designing experiments can be a job in itself.
Study shows Google favored over other search engines by webmasters
Web site policy makers who use robots.txt files as gatekeepers to specify what is open and what is off limits to Web crawlers have a bias that favors Google over other search engines, say Penn State researchers whose study of more than 7,500 Web sites revealed Google's advantage.
Online game feeds music search engine project at UC San Diego
UC San Diego electrical engineers and computer scientists are working together on a computerized system that will make it easy for people who are not music experts (like the senior author's mom) to find the kind of music they want to listen to - without knowing the names of artists or songs.
New proteomics research promises to revolutionize biomedical discovery
Human cells function through the concerted action of thousands of proteins that control their growth and differentiation. Yet, the specific function of most human proteins remains either unknown or poorly characterized.
Key science Web sites buried in information avalanche
As more and more people are turning to the Internet to find information, important science websites are in danger of becoming buried in the sheer avalanche of facts now available online. Key science sites are failing to register in the top 30 Google search results.
IU informatics researchers throttle notion of search engine dominance
Search engines are not biased toward popular Web sites, and may even be egalitarian in the way they direct traffic.
Enterprise management facilities for public authorities
Public authorities have long needed the equivalent of the enterprise management system - as used by leading companies around the world - but seldom had the resources to afford it. Now a new collaborative-working platform developed under the ICTE-PAN project may hold the solution.
Adding semantics to the Web
"The Web will become more than what we see on our computer screens, it will become a place where computers interact with each other and where meaning is attached to information." That is the vision behind a cutting-edge Semantic Web project.
Adding more meaning from place searches
Trawling the web for place-related information is tedious at the best of times. A new search engine, being tested in Europe, recognises geographical terminology and has the intelligence to understand the searches and match them to places.
Firing up knowledge for fire-fighters
Major industrial fires and incidents involving hazardous materials often place fire-fighters in the most dangerous situations of their working lives. Yet as such occurrences are rare, many will face these situations for the first time with little foreknowledge of such incidents. RIMSAT aimed to improve the odds in the fire-fighters' favour.
More Search Engine News Articles
| © 2008 BrightSurf.com |