 |
|
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 Current Events and Search Engine News RSSA new system preserves the right to privacy in Internet searches
A team of Catalan researchers has developed a protocol to distort the user profile generated by Internet search engines, in such a way that they cannot save the searches undertaken by Internet users and thus preserve their privacy. The study has been published in the Computer Communications magazine.
Electrical engineers go head to head with Genius on music playlists
Electrical engineers recently pitted Genius - the music recommendation system in Apple's iTunes - against two experimental music recommender systems.
Researchers find clear difference in quality, type of lung cancer info available in US and Japan
A study published in the July 2009 issue of the Journal of Thoracic Oncology revealed that internet-based lung cancer information was of a higher quality in the United States (US) than in Japan.
If at first you don't succeed, let the search engine try
No matter how good a search engine is, it is sometimes necessary to change the search terms to get the information you need. But what if you did not have to change the search terms yourself? What if the search engine could do that for you?
Social networking for terrorists
A new approach to analyzing social networks, reported in the current issue of the International Journal of Services Sciences, could help homeland security find the covert connections between the people behind terrorist attacks.
Researchers predict click-through behavior in Web searches
In the world of search engines, clicks mean cash, and in a sluggish economy, companies can benefit by maximizing click-throughs to their Web sites from search engines.
Ad click-through rate lower than previously thought
The rate of ad clicks from sponsored and non-sponsored links was reported in a recent study conducted by researchers from Penn State and the Queensland University of Technology.
European computer scientists seek new framework for computation
There have been several revolutions during the 60 year history of electronic computation, such as high level programming languages and client/server separation, but one key challenge has yet to be fully resolved.
Scientists 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.
More Search Engine Current Events and Search Engine News Articles
 |
Search Engine Optimization: Your Visual Blueprint for Effective Internet Marketing by Kristopher B. Jones (Author) Welcome to the only guidebook series that takes a visual approach to professional-level computer topics. Open the book and youll discover step-by-step screen shots that demonstrate over 140 key search engine optimization techniques, including analyzing your competition, researching and analyzing keywords, developing your link building skills, and setting up blogs and communities. Succinct explanations will walk you through using Google Analytics, networking with Facebook and MySpace, setting up pay-per-click campaigns, and much more. |
 |
Search Engines: Information Retrieval in Practice by Bruce Croft (Author), Donald Metzler (Author), Trevor Strohman (Author) KEY BENEFIT: Written by a leader in the field of information retrieval, this text provides the background and tools needed to evaluate, compare and modify search engines. KEY TOPICS: Coverage of the underlying IR and mathematical models reinforce key concepts. Numerous programming exercises make extensive use of Galago, a Java-based open source search engine. MARKET: A valuable tool for search engine and information retrieval professionals. |
 |
Search Engine Optimization For Dummies (For Dummies (Computer/Tech)) by Peter Kent (Author) Why do some sites pop to the top when you search? How do you make yours one of them? You create sites that make search engines happy — that’s what search engine optimization is all about. Search Engine Optimization For Dummies has been the leading resource on how to make that happen, and this third edition is completely updated to cover the newest changes, standards, tips, and tricks. This handy guide shows you how to get more visitors by getting more visibility for your Web site. Find out which search engines matter most, what they look for (and what they hate,) how to get your site included in the best indexes and directories, and the most effective ways to spend your advertising dollars. You’ll discover how to: Plan a search engine strategy Build pages... |
 |
Search Engine Optimization: An Hour a Day by Jennifer Grappone (Author), Gradiva Couzin (Author) Back and bracing as ever, Search Engine Optimization: An Hour a Day, Second Edition offers brisk advice, bite-sized tasks, and smart tools to help you increase visibility for your website on the major search engines. In this new edition of their bestselling how-to guide, SEO consultants Jennifer Grappone and Gradiva Couzin offer surprisingly easy do-it-yourself techniques as well as the very latest SEO strategies for small, very small, and large businesses, as well as for bloggers and web designers. |
 |
Understanding Search Engines: Mathematical Modeling and Text Retrieval (Software, Environments, Tools), Second Edition by Michael W. Berry and Murray Browne (Author) “There is no other information retrieval/search book where the heart is the mathematical foundations. This book is greatly needed to further establish information retrieval as a serious academic, as well as practical and industrial, area." ---Jaime Carbonell, Carnegie Mellon University. “Berry and Browne describe most of what you need to know to design your own search engine. Their strength is the description of the solid mathematical underpinnings at a level that is understandable to competent engineering undergraduates, perhaps with a bit of instructor guidance. They discuss the algorithms used by most commercial search engines, so you may find your use of Google and its kind becomes more effective, too.” --George Corliss, Marquette University. “This book gives a... |
 |
Search Engine Marketing, Inc.: Driving Search Traffic to Your Company's Web Site (2nd Edition) by Mike Moran (Author), Bill Hunt (Author) The #1 Step-by-Step Guide to Search Marketing Success...Now Completely Updated with New Techniques, Tools, Best Practices, and Value-Packed Bonus DVD! —David Meerman Scott, Bestselling Author of The New Rules of Marketing and PR |
|
ThatsSEO - Search Engine Optimization News and Tips by Raghavan, Mercy Livi Welcome to ThatsSEO – blog that updates you on search engine optimization tips, tricks and tradesKindle blogs are fully downloaded onto your Kindle so you can read them even when you're not wirelessly connected. And unlike RSS readers which often only provide headlines, blogs on Kindle give you full text content and images, and are updated wirelessly throughout the day. | |
 |
The Truth About Search Engine Optimization by Rebecca Lieb (Author) “Rebecca’s book is chapter-by-chapter gold for anyone who needs to understand how we find information on the Web.” Kevin M. Ryan, Motivity Marketing, Inc., and Chairman of Search Engine Strategies Advisory Board
In this book, leading search optimization expert Rebecca Lieb brings together more than 50 absolutely crucial facts and insights decision-makers must know to drive more web traffic through better search engine placement. The Truth About Search Engine Optimization doesn't deliver abstract theory: it delivers quick, bite-size, just-the-facts information and plain-English explanations that executives, decision-makers, and even small business owners can actually use, no... |
 |
Google's PageRank and Beyond: The Science of Search Engine Rankings by Amy N. Langville (Author), Carl D. Meyer (Author) Why doesn't your home page appear on the first page of search results, even when you query your own name? How do other Web pages always appear at the top? What creates these powerful rankings? And how? The first book ever about the science of Web page rankings, Google's PageRank and Beyond supplies the answers to these and other questions and more. The book serves two very different audiences: the curious science reader and the technical computational reader. The chapters build in mathematical sophistication, so that the first five are accessible to the general academic reader. While other chapters are much more mathematical in nature, each one contains something for both audiences. For example, the authors include entertaining asides such as how search engines make money and... |
 |
Building Search Applications: Lucene, LingPipe, and Gate by Manu Konchady (Author) Lucene, LingPipe, and Gate are popular open source tools to build powerful search applications. Building Search Applications describes functions from Lucene that include indexing, searching, ranking, and spelling correction to build search engines. Use LingPipe and Gate to find the meaning of text to make search applications more useful. With this book you will learn to: - Extract tokens from text using custom tokenizers and analyzers from Lucene, LingPipe, and Gate. |
| © 2009 BrightSurf.com |