The business world has changed due to the 21st century economy, where borders have melted and trades became free. Nowadays,competition is no longer only at the local market level but also at the global level. In this context, the World Wide Web has become a major source of information for companies and professionals to keep track of their complex, rapidly changing, and competitive business environment. A lot of effort is nonetheless needed to collect and analyze this information due to information overload problem and the huge number of web pages to process and analyze. In this paper, we propose the BizRel resource, the first multilingual (French,English, Spanish, and Chinese) dataset for automatic extraction of binary business relations involving organizations from the web.This dataset is used to train several monolingual and cross-lingual deep learning models to detect these relations in texts. Our results are encouraging, demonstrating the effectiveness of such a resource for both research and business communities. In particular, we believe multilingual business relation extraction systems are crucial tools for decision makers to identify links between specific market stakeholders and build business networks which enable to anticipate changes and discover new threats or opportunities. Our work is therefore an important direction toward such tools.

L’extraction de relations reliant des entités par des liens sémantiques à partir de texte a fait l’objet de nombreux travaux visant à extraire des relations génériques comme l’hyperonymie ou spécifiques comme des relations entre gènes et protéines. Dans cet article, nous nous intéressons aux relations économiques entre deux entités nommées de type organisation à partir de textes issus du web. Ce type de relation, encore peu étudié dans la littérature, a pour but l’identification des liens entre les acteurs d’un secteur d’activité afin d’analyser leurs écosystèmes économiques. Nous présentons B IZ R EL, le premier corpus français annoté en relations économiques, ainsi qu’une approche supervisée à base de différentes architectures neuronales pour la classification de ces relations. L’évaluation de ces modèles montre des résultats très encourageants, ce qui est un premier pas vers l’intelligence économique et concurrentielle à partir de textes pour le français.

Pre-trained Transformer-based models are achieving state-of-the-art results on a variety of Natural Language Processing data sets. However, the size of these models is often a drawback for their deployment in real production applications. In the case of multilingual models, most of the parameters are located in the embeddings layer. Therefore, reducing the vocabulary size should have an important impact on the total number of parameters. In this paper, we propose to extract smaller models that handle fewer number of languages according to the targeted corpora. We present an evaluation of smaller versions of multilingual BERT on the XNLI data set, but we believe that this method may be applied to other multilingual transformers. The obtained results confirm that we can generate smaller models that keep comparable results, while reducing up to 45% of the total number of parameters. We compared our models with DistilmBERT (a distilled version of multilingual BERT) and showed that unlike language reduction, distillation induced a 1.7% to 6% drop in the overall accuracy on the XNLI data set. The presented models and code are publicly available.