Temporal expressions—references to points in time or periods of time—are widespread in text, and their proper interpretation is essential for any natural language processing task that requires the extraction of temporal information. Work on the interpretation of temporal expressions in text has generally been pursued in one of two paradigms: the formal semantics approach, where an attempt is ma...

In this report, we present an account of the semantics of the English temporal prepositions. The approach taken here stresses the limited range of expressive possibilities afforded by these words, and pays particular attention to the irregular interactions they exhibit with verb-tense and -aspect. A framework is developed within which the semantics of English temporal expressions can be couched...

This paper presents how an existing temporal processor was adapted to be used by the English Question Answering system developed part of the EU-funded project QALL-ME. Experiments applying the existing temporal processor to questions from the domain of tourism revealed that the existing temporal processor tackles far too many temporal expressions, and this makes it slower than necessary. In lig...

This paper presents a system for recognition and normalization of temporal expressions (TEs) in Serbian texts according to the TimeML specification language. Based on a finite-state transducers methodology, local grammars are designed to recognize calendar dates, times of day, periods of time and durations, to determine the extension of detected expressions, as well as to normalize their values...

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 ...

Most of the recent work on machine learning-based temporal relation classification has been done by considering only a given pair of temporal entities (events or temporal expressions) at a time. Entities that have temporal connections to the pair of temporal entities under inspection are not considered even though they provide valuable clues to the prediction. In this paper, we present a new ap...

This paper describes the construction and annotation of Late Latin Charter Treebank, a set three dependency treebanks (llct1, llct2 llct3) which together contain 1,261 Early Medieval documentary texts (i.e., original charters) written in Italy between ad 714 1000 (about 594,000 tokens). The focusses on matters linguistically or philologically inclined user llct needs to know: criteria charters ...

In this paper we adopt a constraint-based representation of time, Time Calculus (TC), for anchoring temporal expressions in a novel genre, emails. Email is sufficiently different from most studied genres newswire texts, and its highly under-specified nature fits well with our representation. The evaluation of our anchoring system shows that it performs significantly better than the baseline, an...

We present work on tuning the Heideltime system for identifying time expressions in clinical texts in English and French languages. The main amount of the method is related to the enrichment and adaptation of linguistic resources to identify Timex3 clinical expressions and to normalize them. The test of the adapted versions have been done on the i2b2/VA 2012 corpus for English and a collection ...