New publication in Neurocomputing related to Word Vectorization
Scientists from the ENGINE Centre project: Roman Bartusiak, Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko, Maciej Piasecki have published a paper “WordNet2Vec: Corpora Agnostic Word Vectorization Method” in Neurocomputing (IF=3.317).
A complex nature of big data resources demands new methods for structuring especially for textual content. WordNet is a good knowledge source for comprehensive abstraction of natural language as its good implementations exist for many languages. Since WordNet (EN, PL) embeds natural language in the form of a complex network, a transformation mechanism WordNet2Vec is proposed in the paper. It creates vectors for each word from WordNet. These vectors encapsulate general position – a role of a given the word towards all other words in the natural language. Any list or set of such vectors contains knowledge about the context of its component within the whole language. Such word representation can be easily applied to many analytic tasks like classification or clustering. The usefulness of the WordNet2Vec method was demonstrated in sentiment analysis, i.e., classification with transfer learning for the real Amazon opinion textual dataset.
Paper available here: http://www.sciencedirect.com/science/article/pii/S0925231217315217 and on https://arxiv.org/abs/1606.03335