This article presents an integrated cognitive system for automatic video surveillance: in particular, we focus on the task of classifying the actions occurring in a scene. For this purpose, we developed a semantic infrastructure on top of a hybrid computational ontology of actions. The article outlines the core features of this infrastructure, illustrating how the processing mechanisms of the c...

This paper describes a method for automatically extracting and classifying multiword expressions (MWEs) for Urdu on the basis of a relatively small unannotated corpus (around 8.12 million tokens). The MWEs are extracted by an unsupervised method and classified into two distinct classes, namely locations and person names. The classification is based on simple heuristics that take the co-occurren...

Topic signatures are context vectors built for concepts. They can be automatically acquired for any concept hierarchy using simple methods. This paper explores the correlation between a distributional-based semantic similarity based on topic signatures and several hierarchy-based similarities. We show that topic signatures can be used to approximate link distance in WordNet (0.88 correlation), ...

While Named Entity extraction is useful in many natural language applications, the coarse categories that most NE extractors work with prove insufficient for complex applications such as Question Answering and Ontology generation. We examine one coarse category of named entities, persons, and describe a method for automatically classifying person instances into eight finergrained subcategories....

We present a system that implements an end-to-end discourse parser. The system uses a pipeline architecture with seven stages: preprocessing, recognizing explicit connectives, identifying argument positions, identifying and labeling arguments, classifying explicit and implicit connectives, and identifying attribution structures. The discourse structure of a document is inferred based on these c...

We present a method for decoding image semantics using composite region templates (CRTs). The CRTs de ne prototypal spatial arrangements of regions and features in the images. The system classi es unknown images by matching the strings of regions extracted from the images to the templates in a CRT library. We describe the process for generating the CRTs from photographic images by automatically...

We address the problem of semantic mapping using mobile robots. We focus on the problem of mapping activity as a precursor to automatically classifying, modeling and ultimately understanding the usage of space in a typical urban outdoor environment. We propose and compare two methods for activity mapping one based on hidden Markov models and the other based on support vector machines. Both appr...

This paper describes our submission to SemEval2014 Task 9: Sentiment Analysis in Twitter. Our model is primarily a lexicon based one, augmented by some preprocessing, including detection of MultiWord Expressions, negation propagation and hashtag expansion and by the use of pairwise semantic similarity at the tweet level. Feature extraction is repeated for sub-strings and contrasting sub-string ...

Ontology Patterns for the semantic web are closest in spirit to software patterns, e.g. [1]. They are, or should be, motivated by design experience, not philosophical tradition. The software pattern community was launched into prominence as the result of an effort in "software archeology": digging through existing software, observing and cataloging different solution methods, generalizing and c...

Academic publishers, such as Springer Nature, annotate scholarly products with the appropriate research topics and keywords to facilitate the marketing process and to support (digital) libraries and academic search engines. This critical process is usually handled manually by experienced editors, leading to high costs and slow throughput. In this demo paper, we present Smart Topic Miner (STM), ...