EVALITA intends to promote the development of language technologies for Italian, providing a shared framework where different systems and approaches can be evaluated in a consistent manner. In this scenario, the Temporal Expression Recognition and Normalization task (TERN) encourages research on systems capable of automatically detect and normalize Temporal Expressions (TEs) present in Italian ...

Abstract In this corpus-informed cross-linguistic study, we focus on (1) ‘phraseology markers’ (PMs), which are recurrent and fixed word combinations used to demarcate instances of linguistic prefabrication, (2) novelty markers (NMs), conventional expressions that mark novel phrasings either new or familiar conceptualizations. Both classes have been largely neglected in phraseological studies c...

Mucosa-associated lymphoid tissue (MALT) lymphoma is a type of extranodal marginal zone B-cell lymphoma and is a distinct subtype of non-Hodgkin's lymphoma.Primary MALT lymphomas can also occur in the oral cavity, although their appearance in this location is rare. The neoplastic cells of which MALT lymphomas are composed express B-cell antigens and show monotypic immunoglobulin expression with...

Newspaper articles and other natural-language texts describe actions, events, and states of affairs. A crucial first step toward the automatic extraction of information from these texts—for use in such applications as automatic question answering or summarization—is the capacity to identify what events are being described and to make explicit when these events occurred and which temporal relati...

TimeML, TimeBank, and TTK (TARSQI Project) have been playing an important role in enhancement of IE, QA, and other NLP applications. TimeML is a specification language for events and temporal expressions in text. This paper presents the problems and solutions for porting TimeML to Korean as a part of the Korean TARSQI Project. We also introduce the KTTK which is an automatic markup tool of temp...

We present a neural architecture for containment relation identification between medical events and/or temporal expressions. We experiment on a corpus of deidentified clinical notes in English from the Mayo Clinic, namely the THYME corpus. Our model achieves an F-measure of 0.613 and outperforms the best result reported on this corpus to date.

This work addresses the issue of accessing the content of digital texts, in so as it is anchored in time. The aim of this work is twofold: it consists in conciliating a linguistic approach and an applied approach, to participate in the development of new tools for text mining and information retrieval. It is thus both about implementing interaction systems and modeling the semantics of one the ...