A person who knows a word knows much more than its meaning and pronunciation. The contexts in which a word can be used to express a particular meaning are a critical component of word knowledge. The ability to exploit context in order to determine meaning and resolve potential ambiguities is not a uniquely linguistic ability, but it is dramatically illustrated in the ease with which native spea...

We describe an approach taken for automatically associating entries from an on-line encyclopedia with concepts in an ontology or a lexical semantic network. It has been tested with the Simple English Wikipedia and WordNet, although it can be used with other resources. The accuracy in disambiguating the sense of the encyclopedia entries reaches 91.11% (83.89% for polysemous words). It will be ap...

Common large digital text corpora do not distinguish between different meanings of word forms, intense manual effort has to be done for disambiguation tasks when querying for homonyms or polysemes. To improve this situation, we ran experiments with automatic word sense disambiguation methods operating directly on the output of the corpus query. In this paper, we present experiments with topic m...

Finding the right representations for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This article investigates novel techniques for extracting features from n-gram models, Hidden Markov Models, and other statistical language models, including a novel Partial Lattice Markov Random Field model. Experiments on partof-speech tagging and...

Word embeddings play a significant role in many modern NLP systems. However, most prevalent word embedding learning methods learn one representation per word which is problematic for polysemous words and homonymous words. To address this problem, we propose a multi-phase word sense embedding learning method which utilizes both a corpus and a lexical ontology to learn one embedding per word sens...

We query Web Image search engines with words (e.g., spring) but need images that correspond to particular senses of the word (e.g., flexible coil). Querying with polysemous words often yields unsatisfactory results from engines such as Google Images. We build an image search engine, IDIOM, which improves the quality of returned images by focusing search on the desired sense. Our algorithm, inst...

It is well-known that there are polysemous words like sentence whose ‘‘meaning’’ or ‘‘sense’’ depends on the context of use. We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget’s Thesaurus and Grolier’s Encyclopedia). As this work was nearing completion, we observed...

Many education professionals in Britain believe that school pupils have difficulty accessing academic texts because of inadequate knowledge vocabulary. Previous research has suggested some high frequency words used non-specialised contexts meanings can cause problems for pupils. We take corpus techniques the study higher and apply them to a designed aged 11 14, attempting identify such automati...

In this paper we propose an approach to the task of Word Sense Disambiguation problem that uses Class Association Rules to create an e ective and human-understandable rule-based classi er. We present the accuracy of classi cation of selected polysemous words on an evaluation corpus using the proposed method and compare it to other known approaches. We discuss the advantages and weaknesses of a ...

This paper presents an approach that extends the standard approach used for bilingual lexicon extraction from comparable corpora. We focus on the problem associated to polysemous words found in the seed bilingual lexicon when translating source context vectors. To improve the adequacy of context vectors, the use of a WordNetbased Word Sense Disambiguation process is tested. Experimental results...