This paper introduces the polarity classification system used by the SINAI-DW2Vec team for the task 1 at the TASS 2015 workshop. Our approach does not follow the Vector Space Model nor applies syntactic or lexical analyses. This solution is based on a supervised learning algorithm over vectors resulting from concatenating two different weighted vectors. Those vectors are computed using two diff...

This paper deals with the problem of combination of Neural Networks (NN) and traditional statistical pattern classiiers. It is shown that a Neural Network can be used to replace the vector quantizer (VQ) and some feature extraction and feature reduction modules in a discrete pattern recognition system. A criterion for training the NN-weights and the classiier jointly is derived, leading to the ...

The task of Word Sense Disambiguation (WSD) incorporates in its definition the role of ‘context’. We present our work on the development of a tool which allows for automatic acquisition and ranking of ‘context clues’ for WSD. These clue words are extracted from the contexts of words appearing in a large monolingual corpus. These mined collection of contextual clues form a discrimination net in ...

BACKGROUND We present a formalized medical knowledge system using a linguistic approach combined with a semantic net. METHOD Diseases are defined and coded by natural linguistic terms and linked via a complex network of attributes, categories, classes, lists and other semantic conditions. RESULTS We have isolated more than 4600 disease entities (termed pathosoms using a made-up word) with m...

Computational modeling and eye-tracking were used to investigate how phonological and semantic information interact to influence the time course of spoken word recognition. We extended our recent models (Chen & Mirman, 2012; Mirman, Britt, & Chen, 2013) to account for new evidence that competition among phonological neighbors influences activation of semantically related concepts during spoken ...

Word embeddings have become widelyused in document analysis. While a large number of models for mapping words to vector spaces have been developed, it remains undetermined how much net gain can be achieved over traditional approaches based on bag-of-words. In this paper, we propose a new document clustering approach by combining any word embedding with a state-of-the-art algorithm for clusterin...

Random walks over large knowledge bases like WordNet have been successfully used in word similarity, relatedness and disambiguation tasks. Unfortunately, those algorithms are relatively slow for large repositories, with significant memory footprints. In this paper we present a novel algorithm which encodes the structure of a knowledge base in a continuous vector space, combining random walks an...

objectives: stuttering is one of the most prevalent speech and language disorders. symptomology of stuttering has been surveyed from different aspects such as biological, developmental, environmental, emotional, learning and linguistic. previous researches in english-speaking people have suggested that some linguistic features such as word meanings may play a role in the frequency of speech non...

II THE REPRESENTATION Usually semantic parsers of NLU systems rely on some type of 'deep cases' (Riesbeck and Schank, 1976), (Trost and Steinacker, 1981) to control analysis. While we do not want to deny the advantages of such an approach (we use it ourselves), we propose to apply a different approach in order to analyse words that derive their meaning from the semantic category of their depend...

One question in word production is how the presence of a semantically related word affects the naming process. It has been suggested that semantic effects in picture-word interference tasks are a net result of both inhibitory and facilitatory processes that take place at different processing levels. Finkbeiner and Caramazza (2006) argued that masking distractor words removes the inhibitory comp...