Event Ordering Using TERSEO System

Abstract

In this paper, a method of event ordering based on temporal information resolution is presented. This method consists of two main steps: on the one hand, the recognition and resolution of the temporal expressions that can be transformed on a date, and therefore these dates establish an order between the events that contain them. On the other hand, the detection of temporal signals, for example after, that can not be transformed on a concrete date but relate two events in a chronological way. This event ordering method can be applied to Natural Language Processing systems, for example: Summarization, Question Answering, etc. It is important to emphasize that the event ordering method is based on a multilingual temporal information resolution system. Moreover, this multilinguality has been automatically obtained from a monolingual system (Spanish). The evaluation of the multilingual system is also shown in this paper, achieving a precision of 88% for Spanish and 77% for English.

Approaches to Temporal Expression Recognition in Hindi

“…A good amount of successful research has been accomplished in temporal expression annotation of several languages, for example English [Mani et al 2001], Italian [Negri and Marseglia 2004], Spanish [Saquete et al 2006], German [Strötgen and Gertz 2013] and Chinese [Hacioglu et al 2005]. Starting from the work on TIMEX at the Message Understanding Conference [MUC-7 1998] through recent approaches like Time Aware Information Access (TAIA) [Shokouhi 2012], several temporal annotation systems have been developed and deployed.…”

Automatic transformation from TIDES to TimeML annotation

“…1 This evaluation has been repeated since then as part of the Automatic Content Extraction (ACE) program. 2 The most important automatic annotation systems 3 using TIDES as output are: ATEL (Hacioglu et al 2005), a system developed by Center for Computational Language and Education Research at the University of Colorado, implementing a machine learning approach for identification in English and Chinese; Chronos (Negri 2007), a knowledge-based system developed by Fondazione Bruno Kessler (FBK-irst), which is able to recognize and normalize temporal expressions in developed by the MITRE Corporation, which combines hand-coded patterns with machine learning rules to tag documents; DANTE (Mazur and Dale 2007), developed at the Center for Language Technology at Macquarie University, a system which performs recognition and normalization of temporal expressions in English, where the interface between various components is based on representing the local semantics of temporal expressions; TimexTag (Ahn et al 2005;Ahn 2006), developed at the University of Amsterdam, a system applying data-driven methods for recognition and normalization tasks; and finally, TERSEO (Saquete et al 2006), a system developed at the University of Alicante, which is a knowledge based system for Spanish that has been automatically extended to other languages, such as English, Italian and Catalan.…”

“…For this task, any system which recognizes and normalizes temporal expressions could be used. In our approach, TERSEO system is used because this system recognizes and normalizes (Saquete et al 2006). After computing, if the result is not a complete ISO-format date, then temporalFunction=''true'' must be added to the TIMEX3 tag.…”

“…Some systems use rule-based approaches (Saquete et al 2006), whereas others are using machine learning approaches (Saquete et al 2008;TempEx 2008;Gerber et al 2002). Choosing the appropriate approach depends on the available resources and the requirements of the systems being developed.…”

Combining automatic acquisition of knowledge with machine learning approaches for multilingual temporal recognition and normalization

“…We took advantage of the architecture of an existing rule-based system developed for Spanish (TER-SEO, see [37]), where the recognition model is language-dependent but the normalizing procedure is completely language independent. In this way, the approach is capable of learning the recognition model automatically, adjusting the set of normalization rules using different available resources.…”