论文信息 - FBK-HLT-time : a complete Italian Temporal Processing system for EVENTI-Evalita 2014

FBK-HLT-time : a complete Italian Temporal Processing system for EVENTI-Evalita 2014

English. In this paper we present an endto-end system for temporal processing of Italian texts based on a machine learning approach, specifically supervised classification. The system participated in all subtasks of the EVENTI task at Evalita 2014 (identification of time expressions, events, and temporal relations), including the pilot task on historical texts. Italiano. In questo articolo presentiamo un sistema end-to-end per l’analisi temporale su testi in italiano basato su algoritmi di apprendimento automatico (classificazione supervisionata). Il sistema ha partecipato a tutti i sottotask di EVENTI a Evalita 2014 (individuazione di espressioni di tempo, eventi e relazioni temporali), incluso il task pilota relativo a testi storici.

Paramita Mirza

[1] Tommaso Caselli,et al. Data-Driven Approach Using Semantics for Recognizing and Classifying TimeML Events in Italian , 2011, RANLP.

[2] Emanuele Pianta,et al. The TextPro Tool Suite , 2008, LREC.

[3] Paramita Mirza,et al. Classifying Temporal Relations with Simple Features , 2014, EACL.

[4] Steven Bethard,et al. A Synchronous Context Free Grammar for Time Normalization , 2013, EMNLP.

[5] James Pustejovsky,et al. SemEval-2013 Task 1: TempEval-3: Evaluating Time Expressions, Events, and Temporal Relations , 2013, *SEMEVAL.

[6] Leon Derczynski,et al. TIMEN: An Open Temporal Expression Normalisation Resource , 2012, LREC.

[7] James Pustejovsky,et al. Machine Learning of Temporal Relations , 2006, ACL.

[8] Michael Gertz,et al. HeidelTime: Tuning English and Developing Spanish Resources for TempEval-3 , 2013, *SEMEVAL.

[9] Michael Gertz,et al. Time for More Languages , 2014, ACM Trans. Asian Lang. Inf. Process..