255 research outputs found
Computación del significado en diálogos
No full textTesis doctoral realizada en la Universidad de Tilburg por Roser Morante Vallejo
bajo la dirección de Harry Bunt (Tilburg Univ.). La defensa de la tesis tuvo lugar el 3
de diciembre de 2007 ante el tribunal formado por los doctores David Traum (Univ. of
Southern California), Michael McTear (Univ. of Ulster), Reinhard Muskens (Tilburg Univ.),
Emiel Krahmer (Tilburg Univ.) y Robbert-Jan Beun (Utrecht Univ.).PhD Thesis written by Roser Morante Vallejo at Tilburg University under the supervision of Harry Bunt (Tilburg Univ.). The thesis defence (viva voce) took place before the
committee formed by doctors David Traum (Univ. of Southern California), Michael McTear
(Univ. of Ulster), Reinhard Muskens (Tilburg Univ.), Emiel Krahmer (Tilburg Univ.) and
Robbert-Jan Beun (Utrecht Univ.) on the 3rd of December 2007
Beyond sentence-level semantic role labeling: linking argument structures in discourse
No full textSemantic role labeling is traditionally viewed as a sentence-level task concerned with identifying semantic arguments that are overtly realized in a fairly local context (i.e., a clause or sentence). However, this local view potentially misses important information that can only be recovered if local argument structures are linked across sentence boundaries. One important link concerns semantic arguments that remain locally unrealized (null instantiations) but can be inferred from the context. In this paper, we report on the SemEval 2010 Task-10 on “Linking Events and Their Participants in Discourse”, that addressed this problem. We discuss the corpus that was created for this task, which contains annotations on multiple levels: predicate argument structure (FrameNet and PropBank), null instantiations, and coreference. We also provide an analysis of the task and its difficulties
NEGES 2018 Task 1:Annotation guidelines
No full textThis paper presents task 1 of NEGES 2018, Workshop on Negation in Spanish, held as part of the XXXIV edition of the International Conference of the Spanish Society for Natural Language Processing. The objective of this task is to reach an agreement on the guidelines to follow for the annotation of negation in Spanish texts in order to develop negation processing systems.</p
NEGES 2018 task 2:Negation cues detection
No full textThe XXXIV International Conference of the Spanish Society for the Natural Language Processing (SEPLN 2108) hosted the workshop on Negation in Spanish (NEGES 2018). The second shared task was dedicated to identifying the negation cues. This article presents the specifications, the data set and the evaluation criteria of the task. Moreover, an overview of participating systems is provided and their results are summarised.</p
Design and Analysis of Rotary Positive Displacement Mechanism for Oil-Less Compression
No full textAuthor(s): Holger Roser University of Technology Sydney, Sydney, NSW, Australia In this paper, a simple positive displacement mechanism is investigated, which comprises two counter-rotating meshing rotors within a casing. Although considered for various applications more than a century ago, the basic geometry of this mechanism has not been further explored or adapted to modern gas compressor technology
chroniclingnovelty/chronicles-datasets: Kronieken dataset
No full textThis repository contains the (annotated) XML files of the corpus of early modern chronicles that was created in the context of the NWO project Chronicling Novelty. New knowledge in the Netherlands 1500-1850, which ran from 2018 to 2024.Creators: Judith Pollmann, Erika Kuijpers, Carolina Lenarduzzi, Theo Dekker, Alie Lassche, Roser Morante and with the help of many student assistants and volunteers, see the credits file.Scans of the manuscripts together with the transcriptions and annotations can be viewed and searched on this website.Notes on the individual chronicles and their authors can be found here.Europe 1000-1800: Collective Identities and Transnational Network
Proceedings of the Workshop on Negation and Speculation in Natural Language Processing, Uppsala, Sweden, July 2010
No full text
Recent advances in processing negation
No full textNegation is a complex linguistic phenomenon present in all human languages. It can be seen as an operator that transforms an expression into another expression whose meaning is in some way opposed to the original expression. In this article, we survey previous work on negation with an emphasis on computational approaches. We start defining negation and two important concepts: scope and focus of negation. Then, we survey work in natural language processing that considers negation primarily as a means to improve the results in some task. We also provide information about corpora containing negation annotations in English and other languages, which usually include a combination of annotations of negation cues, scopes, foci, and negated events. We continue the survey with a description of automated approaches to process negation, ranging from early rule-based systems to systems built with traditional machine learning and neural networks. Finally, we conclude with some reflections on current progress and future directions. </p
- …
