Automatic resolution rule assignment to multilingual temporal expressions using annotated corpora

The knowledge-based system TERSEO was originally developed for theRecognition and Normalization of temporal expressions in Spanish andthen extended to other languages: to English first, through theautomatic translation of the temporal expressions, and then toItalian, applying a porting process where the automatic translation ofthe rules was combined with the extraction of expressions from anannotated corpus.In this paper we present a new automatic porting procedure, whereresolution rules are automatically assigned to the temporalexpressions that have been acquired in a new language, thuseliminating the need for automatic translation and consequentlyminimizing the errors produced. This is achieved by exploiting therules of the temporal model, which are language independent, and theinformation extracted from the annotated corpus.Evaluation results of the updated version of TERSEO for English show aconsiderable improvement in recognition performance (+14%F-Measure) with respect to the original system.