This paper describes the system that was submitted in the *SEM 2013 Semantic Textual Similarity shared task. The task aims to find the similarity score between a pair of sentences. We describe a Universal Networking Language (UNL) based semantic extraction system for measuring the semantic similarity. Our approach combines syntactic and word level similarity measures along with the UNL based se...

A general model is described that views similarity judgment as a contrasting of product features. The relative influence of common and distinctive features on perceived similarity is considered a function of the context or task environment. A memory probe is used to measure the common and distinctive features consumers associate with various products. The feature measures are then used to estim...

The authors investigated the ability of 9- to 11-year-olds and of adults to use similarity-based and rule-based processes as a function of task characteristics in a task that can be considered either a categorization task or a multiple-cue judgment task, depending on the nature of the criterion (binary vs. continuous). Both children and adults relied on similarity-based processes in the categor...

This paper briefly reports our submissions to the Semantic Textual Similarity (STS) task in the SemEval 2012 (Task 6). We first use knowledge-based methods to compute word semantic similarity as well as Word Sense Disambiguation (WSD). We also consider word order similarity from the structure of the sentence. Finally we sum up several aspects of similarity with different coefficients and get th...

Semantic Textual Similarity is the task of finding the degree of similarity between a pair of sentences through semantics extraction. This is motivated by the fact that syntactically diverse sentences often convey the same meaning. This paper describes the approach that was used in the *SEM Shared Task 2013. The approach combines semantic, syntactic and lexical similarity measures for finding s...

Multiple people detection and tracking is a challenging task in real-world crowded scenes. In this paper, we have presented an online multiple people tracking-by-detection approach with a single camera. We have detected objects with deformable part models and a visual background extractor. In the tracking phase we have used a combination of support vector machine (SVM) person-specific classifie...

Relative similarity learning (RSL) aims to learn similarity functions from data with relative constraints. Most previous algorithms developed for RSL are batch-based learning approaches which suffer from poor scalability when dealing with realworld data arriving sequentially. These methods are often designed to learn a single similarity function for a specific task. Therefore, they may be sub-o...