General learning approach for event extraction: Case of management change event

Samir Elloumi (1) , Ali Jaoua (1) , Fethi Ferjani (1) , Nasredine Semmar (2) , Romaric Besancon (2) , Jihad Al-Jaam (1) , Helmi Hammami (3)

1 Computer Science and Engineering Department [Doha] (University of Qatar, College of Engineering)
2 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs
3 College of Business and Economics, Qatar University

Starting from an ontology of a targeted financial domain corresponding to transaction, performance and $management\ change$ news, relevant segments of text containing at least a domain keyword are extracted. The linguistic pattern of each segment is automatically generated to serve initially as a learning model. Each pattern is composed of named entities, keywords and articulation words. Some generic named entities like organizations, persons, locations, dates and grammatical annotations are generated by an automatic tool. During the learning step, each relevant segment is manually annotated with respect to the targeted entities (roles) structuring an event of the ontology. Information extraction is processed by associating a role with a specific entity. By alignment of generic entities to specific entities, some strings of a text are automatically annotated. An original learning approach is presented. Experiments with the $management\ change$ event showed how recognition rates are improved by using different generalization tools.

Mots clés: automatic pattern generation; generic model; information extraction levels; management change event; named entities

Domaines: Automatique; Sciences de l'ingénieur [physics]; Gestion et management

Samir Elloumi, Ali Jaoua, Fethi Ferjani, Nasredine Semmar, Romaric Besancon, et al.. General learning approach for event extraction: Case of management change event. Journal of Information Science, 2013, 39, pp.211 - 224. ⟨10.1177/0165551512464140⟩. ⟨cea-01777948⟩