The problem of question/answering (Q/A) is to find answers to open-domain questions by searching large collections of documents. Unlike information retrieval systems, very common ...
Mihai Surdeanu, Dan I. Moldovan, Sanda M. Harabagi...
This paper describes a learning system, LASSY1, which explores domains represented by Prolog databases, and use its acquired knowledge to increase the efficiency of a Prolog inter...
In this paper, we present a prototype that helps visualizing the relative importance of sentences extracted from medical texts using Embodied Conversational Agents (ECA). We propo...
The Table Lens is a visualization for searching for patterns and outliers in multivariate datasets. It supports a lightweight form of exploratory data analysis (EDA) by integratin...
An approach to detection of phishing webpages based on visual similarity is proposed, which can be utilized as a part of an enterprise solution for anti-phishing. A legitimate web...
Liu Wenyin, Guanglin Huang, Liu Xiaoyue, Zhang Min...