Research on WSD has been rather intensive in the last quarter of the 20th c. (Agirre & Edmond 2006). Difficulties for a successful disambiguation algorithm lie mainly in polysemous words with high granularity. A research project recently conducted by Sanchez, Cantos, Almela (Sánchez, Cantos & Almela 2007; 2008), grounded on a supervised method, proved that the success rate is clearly lower in w...

Concept name similarity calculation between ontologies is the basis of ontology mapping. Many concept name words are polysemous, but in traditional word similarity algorithms, the similarity between the most similar senses of two words was regarded as the word similarity. It were ignored that the true meanings of concept names in the context, which resulted in falling of the precision of simila...

We present two problems for statistically extracting bilingual lexicon: (1) How can noisy parallel corpora be used? (2) How can non-parallel yet comparable corpora be used? We describe our own work and contribution in relaxing the constraint of using only clean parallel corpora. DKvec is a method for extracting bilingual lexicons, from noisy parallel corpora based on arrival distances of words ...

unless there is a specific statement to the contrary. The three categories – animate, concrete, abstract are not discrete. They are rendered porous by the polysemy of the English language. A common example is the noun chair, which might be concrete (an item of furniture) or animate (the person responsible for the process of a meeting). Connell and Lynott (2012: 461) cite substitute and kingdom ...

Knowledge acquisition is an essential and intractable task for almost every natural language processing study. To date, corpus approach is a primary means for acquiring lexical-level semantic knowledge, but it has the problem of knowledge insufficiency when training on various kinds of corpora. This paper is concerned with the issue of how to acquire and represent conceptual knowledge explicitl...

The work presented in this paper explores a supervised method for learning a probabilistic model of a lexicon of VerbNet classes. We intend for the probabilistic model to provide a probability distribution of verb-class associations, over known and unknown verbs, including polysemous words. In our approach, training instances are obtained from an existing lexicon and/or from an annotated corpus...

We present a framework for using continuousspace vector representations of word meaning to derive new vectors representing the meaning of senses listed in a semantic network. It is a post-processing approach that can be applied to several types of word vector representations. It uses two ideas: first, that vectors for polysemous words can be decomposed into a convex combination of sense vectors...

A neural network model is constructed to mimic the processing involved in semantic and working memory when subliminal effects are involved. These effects involve modifications of reaction time to later inputs, according as to whether or not there has been conscious or unconscious processing of the earlier input. The model is constructed of two separate modules, one (a semantic memory module) al...