No abstract

No abstract

We present in this paper our system developed for SemEval 2015 Shared Task 2 (2a -English Semantic Textual Similarity, STS, and 2c -Interpretable Similarity) and the results of the submitted runs. For the English STS subtask, we used regression models combining a wide array of features including semantic similarity scores obtained from various methods. One of our runs achieved weighted mean correlation score of 0.784 for sentence similarity subtask (i.e., English STS) and was ranked tenth among 74 runs submitted by 29 teams. For the interpretable similarity pilot task, we employed a rule-based approach blended with chunk alignment labeling and scoring based on semantic similarity features. Our system for interpretable text similarity was among the top three best performing systems.

No abstract

No abstract

We present in this paper an innovative solution to the challenge of building effective educational technologies that offer tailored instruction to each individual learner. The proposed solution in the form of a conversational intelligent tutoring system, called DeepTutor, has been developed as a web application that is accessible 24/7 through a browser from any device connected to the Internet. The success of several large scale experiments with high-school students using DeepTutor is a solid proof that conversational intelligent tutoring at scale over the web is possible.

International audiencePeer-to-Peer (P2P) technology has been shown to be effective for content delivery on the Internet. Its applications such as video streaming on Mobile Ad hoc NETwork (MANET) has been explored while the issue of live video streaming on MANET is still a real challenge due to frequent changes in network topology, and the sensitiveness of radio links. To combat these challenges, we propose a novel Cross-Layer And P2P based Solution (CLAPS) that distributes a live video stream using an overlay constructed by the Multicast Overlay Spanning Tree (MOST) protocol. In this solution we have adopted the Multiple Description Coding (MDC) to create multiple video descriptions for a given video stream. CLAPS then distributes pieces to the closest peer which on its turn shares the pieces among the interested peers using the MOST protocol. We compared the performances of the CLAPS with that of the original MOST and we showed that in most of the cases CLAPS substantially increases the continuity index of the video stream and significantly, CLAPS performs better with high mobility and with more than one video strea

Social media texts such as blog posts, comments, and tweets often contain offensive languages including racial hate speech comments, personal attacks, and sexual harassments. Detecting inappropriate use of language is, therefore, of utmost importance for the safety of the users as well as for suppressing hateful conduct and aggression. Existing approaches to this problem are mostly available for resource-rich languages such as English and German. In this paper, we characterize the offensive language in Nepali, a low-resource language, highlighting the challenges that need to be addressed for processing Nepali social media text. We also present experiments for detecting offensive language using supervised machine learning. Besides contributing the first baseline approaches of detecting offensive language in Nepali, we also release human annotated data sets to encourage future research on this crucial topic.