The extraction of multi-word relevante xpressions has been an increasingly hot topic in the last few years. Relevant expressions are applicable in diverse areas such as Information Retrieval, document clustering, or classiﬁcation and indexing of documents. However, relevant single-words, which represent much of the knowledge in texts, have been a relatively dormant ﬁeld. In this paper we present a statistical language-independent approach to extract concepts formed by relevant single and multi-word units. By achieving promising precision/recall values, it can be an alternative both to language dependent approaches and to extractors that deal exclusively with multi-words.
|Title of host publication||SciVerse ScienceDirect, Procedia Computer Science|
|Publication status||Published - 1 Jan 2012|
|Event||International Conference on Computational Science - |
Duration: 1 Jan 2012 → …
|Conference||International Conference on Computational Science|
|Period||1/01/12 → …|