CLaC-CORE, an exhaustive feature combination system ranked 4th among 34 teams in the Semantic Textual Similarity shared task STS 2013. Using a core set of 11 lexical features of the most basic kind, it uses a support vector regressor which uses a combination of these lexical features to train a model for predicting similarity between sentences in a two phase method, which in turn uses all combi...

This paper centers on ancient, generally rather scattered and elusive remains of gameplay. Focusing on a discreteassemblage of game-related artefacts from the Bronze Age Indus Valley urban settlement of Mohenjo-daro, it conductsa detailed study of some of the patchy features to see whether more structured elements thereby can be distinguished.The finds are approached situated in a broader, game...

Aiming at highlighting the important role of print media discourse in the implicit  transfer of  the dominant ideology of discourse context, the present data-driven paper demonstrates  how the lexical features of repetition and synonymy as well as the structural and thematic features of passivization, nominalization and predicated theme were utilized by the discourse producers to mediate betwee...

This year, we participated in TRECVID 2010 content-based copy detection task. In this notebook paper we will describe our work in details. Different from last year when we just used SURF (speeded up robust feature) as visual feature, this year we employed a combination of four different features for our rough detection process: global SURF, center SURR, global color correlogram and center corre...

The culmination of the 2002 RoboFlag Summer Undergraduate Research Fellowship program, jointly operated between California Institute of Technology and Cornell University, was a final competition between two teams of three undergraduate researchers. After ten weeks of preparation, Team Pasadena defeated Team Ithaca in two of the three final games. This paper provides the detailed results of the ...

A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature space (also known as attribute-value descriptions). A teacher partitions a set of training examples into a finite number of classes. The task of the learning algorithm is to induce a concept from the training examples....

articles in general and definite articles in particular can create problems even long after all other aspects of english have been mastered. the present article investigated the learnability problems related to the acquisition of count-mass distinction of english nominals by persian l2 learners. the theoretical underpinning of the study is the interpretability hypothesis (tsimpli & dimitrak...

Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods. In this paper, we propose a learnable histogram layer, which learns histogram features within deep neural networks in end-to-end training. Such a layer is abl...

The context in which a search takes place affects the Information Retrieval (IR) process. It affects the searcher’s interaction with the IR system, his expectations and his decisions about the documents he retrieves. Therefore, knowing more about what features are important in a searcher’s context and what they are used for, can help design more useful and successful IR systems. This paper has ...