Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Measuring Semantic Similarity between Short Texts

Mihai LinteanUniversity of Memphis[Home Page]

Notice:  Hosted by Vinay Chaudhri.

Date:  2012-07-12 at 16:00

Location:  EJ228 (SRI E building)  (Directions)

   Abstract

Measuring semantic similarity is a central problem in Natural Language Processing due to its importance to a variety of applications ranging from web-page retrieval; question answering, text classification and clustering, to natural language generation and dialog-based systems. As a concrete example, in Intelligent Tutoring Systems (ITSs), students are sometimes required to respond in free form natural language to specific tasks given by the virtual tutor. These free form answers must then be automatically analyzed for accuracy. The typical approach is to evaluate them, based on how similar they are to some predefined answers, which are handcrafted beforehand by human experts. Semantic similarity can be measured at different levels: from words and phrases, to paragraphs and documents. In this talk, I will present my work on measuring semantic similarity between short texts. Several methods are being studied to compare the representations, ranging from simple lexical overlap, to more complex methods such as comparing semantic representations in vector spaces as well as syntactic structures. Furthermore, a few powerful kernel models are proposed to use in combination with Support Vector Machine (SVM) classifiers for the case in which the semantic similarity problem is modeled as a classification task. I will also briefly describe a java-based, user friendly tool that offers various configurable metrics to compute the similarity. The tool also offers ways to evaluate and compare these metrics on given datasets of binary classified examples, confirming or denying the existence of similarity relations such as paraphrase or entailment.

   Bio for Mihai Lintean

Mihai Lintean is currently a Postdoctoral Research Fellow in the Computer Science Department at the University of Memphis; working with Dr. Vasile Rus to research and develop dialogue based tutoring systems for teaching conceptual physics to high school students. He recently received his doctoral degree from the same university and a master and bachelor’s degrees in Computer Science from Babes-Bolyai University of Cluj-Napoca, Romania. Mihai¬ís primary research interests are in Natural Language Processing (NLP), with focused applicability on educational technologies such as intelligent tutoring systems. Particularly he is interested in measuring semantic similarity between texts, representing knowledge through relational diagrams of concepts, automatic generation of questions, and using various machine learning techniques to solve other complex NLP problems. Mihai has published numerous papers and articles in reputable, peer-reviewed conferences and journals. He currently serves as co-chair of the Applied Natural Language Processing Special Track at the 25th International Conference of the Florida Artificial Intelligence Research Society (FLAIRS 2012).

   Note for Visitors to SRI

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.

SRI International
©2014 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy