PDF] Near-Synonym Choice using a 5-gram Language Model

Por um escritor misterioso

Descrição

An unsupervised statistical method for automatic choice of near-synonyms is presented and compared to the stateof-the-art and it is shown that this method outperforms two previous methods on the same task. In this work, an unsupervised statistical method for automatic choice of near-synonyms is presented and compared to the stateof-the-art. We use a 5-gram language model built from the Google Web 1T data set. The proposed method works automatically, does not require any human-annotated knowledge resources (e.g., ontologies) and can be applied to different languages. Our evaluation experiments show that this method outperforms two previous methods on the same task. We also show that our proposed unsupervised method is comparable to a supervised method on the same task. This work is applicable to an intelligent thesaurus, machine translation, and natural language generation.