, Il est difficile de savoir pourquoi les performances diffèrent par relation alors que certaines comme "country of birth" et "country of death" pourraient sembler être de difficulté analogue, et "residents of stateorprovince", qui figurent dans les derniers intervalles

, Nous avons proposé un ensemble de traits permettant de caractériser l'expression d'une relation dans les textes, mais aussi, nous avons introduit des traits calculés à un niveau global. Ceux-ci sont calculés sur la présence des entités et relations dans l'ensemble de la collection et, ce qui constitue une nouveauté pour cette tâche, sur des graphes de communauté permettant de rendre compte de connaissances générales sur les entités provenant des entités auxquelles elles sont liées. Nous avons montré que nos ensembles de traits permettent d'améliorer une baseline construite à

, Le calcul des différentes caractéristiques est dépendant de la capacité d'analyse des textes, notamment des résultats du système d'annotation en entité nommées. Il faudra améliorer cette partie de manière à pouvoir évaluer l'apport des graphes de communauté sur plus d'exemples

P. Bonacich and P. Lloyd, « Eigenvector-like measures of centrality for asymmetric relations, Social networks, vol.23, issue.3, pp.191-201, 2001.

R. C. Bunescu and R. J. Mooney, « A shortest path dependency kernel for relation extraction, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp.724-731, 2005.

M. F. Chowdhury and A. Lavelli, Combining tree structures, flat features and patterns for biomedical relation extraction, Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, pp.420-429, 2012.

H. Cui, R. Sun, K. Li, M. Kan, and T. Chua, « Question answering passage retrieval using dependency relations, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, pp.400-407, 2005.

A. Culotta and J. Sorensen, Dependency tree kernels for relation extraction, Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p.423, 2004.

D. B. Friedl and J. Heidemann, « A critical review of centrality measures in social networks, Business & Information Systems Engineering, vol.2, issue.6, pp.371-385, 2010.

K. Fundel, R. Küffner, R. Zimmer, and . Relex, Relation extraction using dependency parse trees, Bioinformatics, vol.23, issue.3, pp.365-371, 2007.

P. Gamallo, M. Garcia, and S. Fernández-lanza, « Dependency-based open information extraction », Proceedings of the joint workshop on unsupervised and semi-supervised learning in NLP, pp.10-18, 2012.

X. Han, L. Sun, and J. Zhao, « Collective entity linking in web text : a graph-based method, Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, pp.765-774, 2011.

R. Hoffmann, C. Zhang, X. Ling, L. Zettlemoyer, and D. S. Weld, « Knowledge-based weak supervision for information extraction of overlapping relations, Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics : Human Language Technologies, vol.1, pp.541-550, 2011.

A. Holzinger, B. Ofner, C. Stocker, A. C. Valdez, A. K. Schaar et al., On graph entropy measures for knowledge discovery from publication network data », Availability, reliability, and security in information systems and HCI, pp.354-362, 2013.

B. Magnini, M. Negri, R. Prevete, and H. Tanev, Is it the right answer ? : exploiting web redundancy for Answer Validation », Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp.425-432, 2002.

C. D. Manning, M. Surdeanu, J. Bauer, J. Finkel, S. J. Bethard et al., The Stanford CoreNLP Natural Language Processing Toolkit », Association for Computational Linguistics (ACL) System Demonstrations, pp.55-60, 2014.

M. Mintz, S. Bills, R. Snow, and D. Jurafsky, « Distant supervision for relation extraction without labeled data, Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, vol.2, pp.1003-1011, 2009.

F. Niu, C. Zhang, C. Ré, J. W. Shavlik, and . Deepdive, Web-scale Knowledge-base Construction using Statistical Learning and Inference. », VLDS, vol.12, pp.25-28, 2012.

S. Riedel, L. Yao, and A. Mccallum, « Modeling relations and their mentions without labeled text, Machine Learning and Knowledge Discovery in Databases, pp.148-163, 2010.

M. Sammons, Y. Song, R. Wang, G. Kundu, C. Tsai et al., « Overview of UI-CCG systems for event argument extraction, entity discovery and linking, and slot filler validation, vol.51, p.61801, 2014.

L. Solá, M. Romance, R. Criado, J. Flores, A. G. Del-amo et al., Eigenvector centrality of nodes in multiplex networks, An Interdisciplinary Journal of Nonlinear Science, vol.23, issue.3, p.33131, 2013.

V. Viswanathan, N. F. Rajani, Y. Bentor, and R. Mooney, « Stacked Ensembles of Information Extractors for Knowledge-Base Population, Proceedings of ACL, 2015.

W. Liu, E. Costello, C. Piatko, C. , and «. Tac-kbp2013, Slot Filler Validation System, Proceedings of the Sixth Text Analysis Conference (TAC 2013), vol.24, 2013.

L. Yao, A. Haghighi, S. Riedel, and A. Mccallum, Structured relation discovery using generative models, Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp.1456-1466, 2011.

D. Yu, H. Huang, T. Cassidy, H. Ji, C. Wang et al., The Wisdom of Minority : Unsupervised Slot Filling Validation based on Multidimensional Truth-Finding. », COLING, pp.1567-1578, 2014.