AIC Seminar Series

This talk describes an approach to capturing commonsense knowledge about objects in their properties from non-expert human contributors. Capturing such knowledge will clear the path to more intelligent human-computer interfaces and pave the way for computers to reason about our world. In the domain of natural language processing, it will provide the world knowledge much needed for semantic processing of natural language. In this talk, I will introduce _cumulative analogy_, a class of nearest-neighbor based analogical reasoning algorithms; I will also present theoretical and empirical results about its effectiveness. Finally, I will discuss LEARNER, a deployed system that implements cumulative analogy to collect knowledge (a live system is available at http://teach-computers.org) Specifically, Learner acquires assertion-level knowledge by constructing shallow semantic analogies between a KA topic and its nearest neighbors and then posing these analogies as natural language questions to human contributors. Suppose, for example, that based on the knowledge about ``newspapers'' already present in the knowledge base, Learner judges ``newspaper'' to be similar to ``book'' and ``magazine.'' Further suppose that assertions ``books contain information'' and ``magazines contain information'' are also already in the knowledge base. Then Learner will use cumulative analogy from the similar topics to ask humans whether ``newspapers contain information.'' Because similarity between topics is computed based on what is already known about them, Learner exhibits _bootstrapping_ behavior --- the quality of its questions improves as it gathers more knowledge. By summing evidence for and against posing any given question, Learner (and cumulative analogy) also exhibits _noise tolerance_, limiting the effect of incorrect similarities. Empirically, evaluating the percentages of questions answered affirmatively, negatively and judged to be nonsensical in the cumulative analogy case compares favorably with the baseline, no-similarity case that relies on random objects rather than nearest neighbors. Of the questions generated by cumulative analogy, contributors answered 45% affirmatively, 28% negatively and marked 13% as nonsensical; in the control, no-similarity case 8% of questions were answered affirmatively, 60% negatively and 26% were marked as nonsensical. The central finding reported in the talk is the knowledge acquisition power of shallow semantic analogy from nearest neighbors.

Dr. Timothy Chklovski has joined MIT as an undergraduate in CS and Math in 1994. After a 2.5 years, Dr. Chklovski has continued at MIT as a graduate student in CS. In 1999, he took a leave of absence to found and run aQuery, an NLP document understanding and IR company financed and mentored by Mitchell Kapor and Accel partners. At aQuery, Dr. Chklovski has developed a number of advanced NLP based search engine, text mining, and document understanding technologies. In 2001, Dr. Chklovski has returned to MIT to carry out his doctoral research. Dr. Chklovski holds PhD, Master's and Bachelor's degrees in Computer science, as well as a Bachelor's degree in Math, all from MIT. Russian-born Dr. Chklovski has immigrated to the United States and learned English at the age of 13. From childhood, he has been interested in Artificial Intelligence and problem solving; in '93, his interest in problem solving and mathematics has led him to represent the United States on a team of six at the International Math Olympiad in Istanbul, Turkey. His current interests include knowledge acquisition & representation and natural language processing (esp. lexical semantics).

Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.

©2013 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy