Context-aware Relation Classification based on Deep Learning

Modern information supports carry heterogeneous data, in such large quantities that the traditional means of processing become obsolete and inefficient to meet today's needs. In addition to the quantity of data, the unstructured nature of this data requires new intelligent, efficient and automated processing techniques. In order to produce automatic systems capable of managing this data and extracting relevant knowledge from it, a number of problems must be solved, including the extraction and classification of relations from textual data. While the extraction of relations is mainly based on syntactic aspects of the text, the classification requires a semantic approach. Such existing relation classification systems deal only with few pre-defined types. These systems don't take into account the context, thus reducing the relevance of this classification. In this paper, we propose a simplified definition of what is context and, based on this definition, we propose an approach to classify relations according to their types while taking into account this context. The system, allowing to obtain a degree of "contextualization" of relations, has been tested on the SemEval-2010 Task-8, New York Times corpora and a contextual dataset, named WikiContext, that we have built for this purpose. The results show that our system outperforms the state-of-the-art relation classification systems, thus demonstrating the relevance of taking context into account in this classification process.