Generation of the sense of a sentence in Arabic language with a connectionist approach

For several decades, research on natural language processing (NLP) has been dominated by the symbolic approach. However, during the last few years, there has been increasing interest in the connectionist technical applicability for NLP to converge towards connectionist NLP (CNLP). In this paper, we propose a connectionist model for the generation of an internal representation of the sense of a sentence in the Arabic language, based on semantic cases. We use the backpropagation algorithm in a simple recurrent network. A sentence is analyzed word by word. Every word is introduced to the network according to its semantic features. The task of the network consists of reading the sentence and deciding on a suitable semantic role for each word. The network successfully learned a case role assignment task. It has been experimented with on several corpora. The network has also been tested on a composed corpus of different sizes of sentences (2, 3, 4 and more), and a generalization rate approaching 92% was obtained.