Recent work for learning word representations has applied successfully to many NLP applications, such as sentiment analysis and question answering. However, most of these models assume a single vector per word type without considering polysemy and homonymy. In this paper, we present an extension to the CBOW model which not only improves the quality of embeddings but also makes embeddings suitab...

Cross language information retrieval (CLIR) presents huge ambiguous results as polysemy problems. Therefore, the semantic approach comes to solve the polysemy problem which that the same word may have different meanings according to the context of sentences. This paper presents semantic technique on queries for retrieving more relevant results in CLIR) that concentrates on the Arabic, Malay or ...

Automatic classification of news articles is a relevant problem due to the large amount of news generated every day, so it is crucial that these news are classified to allow for users to access to information of interest quickly and effectively. Traditional classification systems represent documents as bag-of-words (BoW), which are oblivious to two problems of language: synonymy and polysemy. T...

What’s in a word? As it turns out, quite a lot. The vast majority of words in our language, including trademarked terms, signify a variety of conceptual meanings and senses. This idea of splintered definition— described in the psycholinguistics literature as “semantic ambiguity” and offered in two flavors: “homonymy” (divergent and unrelated meanings) and “polysemy” (divergent yet related sense...

We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb use...

This paper considers the use of controlled languages for query translation in a legislative document retrieval system. Problem statement and analysis of the approach are described. The use of controlled languages is motivated by the fact that precision is very important in our case. In many information retrieval systems, the use of unrestricted language resources such as general purpose machine...