In this report we describe the previous research done by our institute in the field of requirement analysis using different natural language processing methods. To represent the different degrees of similarity between words we implemented different methods that make use of synonyms and hyperonyms. We present the strengths of our methods and identify their weaknesses. For our future research we ...

In this work we introduce and describe a language resource composed of lists of simpler synonyms for Spanish. The synonyms are divided in different senses taken from the Spanish OpenThesaurus, where context disambiguation was performed by using statistical information from the Web and Google Books Ngrams. This resource is freely available online and can be used for different NLP tasks such as l...

We explore a semi-supervised approach for improving the portability of time expression recognition to non-newswire domains: we generate additional training examples by substituting temporal expression words with potential synonyms. We explore using synonyms both from WordNet and from the Latent Words Language Model (LWLM), which predicts synonyms in context using an unsupervised approach. We ev...

Despite their similar meanings, near-synonyms may have different usages in different contexts. For second language learners, such differences are not easily grasped in practical use. In this paper, we develop a computer-assisted near-synonym learning system for Chinese English-as-aSecond-Language (ESL) learners using two automatic near-synonym choice techniques: pointwise mutual information (PM...

Biomedical synonyms are important resources for Natural Language Processing in Biomedical domain. Existing synonym resources (e.g., the UMLS) are not complete. Manual efforts for expanding and enriching these resources are prohibitively expensive. We therefore develop and evaluate approaches for automated synonym extraction from Wikipedia. Using the inter-wiki links, we extracted the candidate ...

Near-synonyms are words that mean approximately the same thing, and which tend to be assigned to the same leaf in ontologies such as WordNet. However, they can differ from each other subtly in both meaning and usage—consider the pair of nearsynonyms frugal and stingy—and therefore choosing the appropriate near-synonym for a given context is not a trivial problem. Initial work by Edmonds (1997) ...

1077-3142/$ see front matter 2011 Elsevier Inc. A doi:10.1016/j.cviu.2011.10.004 ⇑ Corresponding author. E-mail address: [email protected] (E. Gavves). In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which assigns words based on closeness in descriptor space, we focus on identifying pairs of independent, distant word...

This study examines near synonyms and tries to extract the contrasts that dictate their semantic and associated syntactic behaviors. A near synonym pair of Chinese verbs, fangbian and bianli, which mean ‘to be convenient’, is under examination. Corpus data reveal some important but opaque distributional differences between this synonym pair that are hard to be recognized solely by intuition. Th...

We propose a method for automatic synonym extraction in a dictionary. Our method is based on an algorithm that computes similarity measures between vertices in graphs. This algorithm can be thought of as a generalization of Kleinberg’s web search algorithm to structure graphs that are more general than the hub-authority graph used by Kleinberg. We use the 1913 Webster’s Dictionary and apply our...

It is estimated that 20% of medical diagnoses is incorrect [7, 9]. This is caused by limited human cognitive abilities. We are unable to know everything about every human on earth, and therefore cannot reason over this data. Cognitive systems such as IBM Watson can expand these cognitive abilities. These systems are able to reason over data, and interpret more effective than humans can. They ar...