Andrés Torres Rivera

Andrés Torres Rivera
Universitat Oberta de Catalunya | UOC · Arts and Humanities Studies

About

7
Publications
1,096
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
12
Citations
Citations since 2016
7 Research Items
12 Citations
2016201720182019202020212022012345
2016201720182019202020212022012345
2016201720182019202020212022012345
2016201720182019202020212022012345
Education
September 2016 - July 2019
September 2015 - July 2019
University Pompeu Fabra
Field of study
  • Translation and Language Sciences
September 2014 - July 2015
University Pompeu Fabra
Field of study
  • Theoretical and Applied Linguistics

Publications

Publications (7)
Conference Paper
Full-text available
In this paper we present a novel resource-inexpensive architecture for metaphor detection based on a residual bidirectional long short-term memory and conditional random fields. Current approaches on this task rely on deep neural networks to identify metaphorical words, using additional linguistic features or word embeddings. We evaluate our propos...
Article
Full-text available
In this paper we propose a neural network approach to detect the metaphoricity of Adjective-Noun pairs using pre-trained word embeddings and word similarity using dot product. We found that metaphorical word pairs tend to have a lower dot product score while literal pairs a higher score. On this basis, we compared seven optimizers and two activatio...
Preprint
Full-text available
Semantic neologisms (SN) are defined as words that acquire a new word meaning while maintaining their form. Given the nature of this kind of neologisms, the task of identifying these new word meanings is currently performed manually by specialists at observatories of neology. To detect SN in a semi-automatic way, we developed a system that implemen...
Article
Full-text available
Semantic neologisms (SN) are defined as words that acquire a new word meaning while maintaining their form. Given the nature of this kind of neologisms, the task of identifying these new word meanings is currently performed manually by specialists at observatories of neology. To detect SN in a semi-automatic way, we developed a system that implemen...
Thesis
Full-text available
En el campo de la neología, se han desarrollado diferentes acercamientos metodológicospara la detección y extracción de neologismos semánticos empleando estrategias comola desambiguación semántica y el modelado de temas, pero todavía no existe una propuestade un sistema para la detección de estas unidades. A partir de un estudio detalladosobre los...
Preprint
In this paper we present Genex+ (Genex plus), an improved implementation of the Genex system (Générateur d'Exemples) [17], by using the semantic closeness between certain fragments of texts. This process was based on the combination of the successive extraction of concordances and colloca-tions with the determination of the semantic closeness by th...

Network

Cited By

Projects

Project (1)
Project
Website: http://mentalhealthmetaphors.uoc.edu/ The MOMENT project aims to contribute to a better understanding of severe mental disorders (schizophrenia, bipolar disorder, severe depression and obsessive-compulsive disorder) by analysing the discourse of the two main groups involved: people with a mental health diagnosis and mental health professionals. This analysis uses the Conceptual Metaphor Theory. The two main objectives are: 1) to detect and systematize dominant conceptualizations of the disorders, and 2) to promote changes in discourse in order to improve public health communication and communications between patients and professionals. SPECIFIC GOALS: 1. To build a hand-annotated corpus of first-person testimonies published online (in blogs, on Twitter, etc.) by patients and professionals in Spain. This corpus will be used both for discourse analysis and as a testing ground for automatic metaphor detection. 2. To analyse first-person accounts from people diagnosed with a severe mental disorder and from mental health professionals in order to detect: 1) what kind of metaphors are used by these two groups when talking about the mental disorder and related experiences, and what similarities and differences there are between groups on two levels, intergroup (patients vs. professionals) and intragroup (type of severe mental disorder and professional profile); and 2) what kind of discourses are built upon the uses of these metaphors: biomedical discourses, which tend to disempower affected people, or alternative humanistic discourses, which tend to promote patients’ agency. 3. To improve the methodology for detecting metaphors and codifying them in corpora, with the aim of contributing to solving the methodological problems common to any application of the Conceptual Metaphor Theory. 4. To improve the methodology for automatic metaphor detection, thus contributing to a cutting-edge area of research in the field of computational linguistics. 5. To contribute to the debate on how we should talk about mental disorders. A compendium of metaphors is going to be created based on the results obtained; this is to promote: 1) public communications about mental health that are more useful and respectful, and 2) better awareness of patients’ narratives among professionals. MULTIDISCIPLINARY RESEARCH TEAM The multidisciplinary team conducting this project shares extensive experience in applied linguistics and in several fields relating to mental health (psychology, social education and medical anthropology). As such, MOMENT is a collaborative project aiming to mobilize knowledge combined from various scientific fields to face one of the great challenges of our society: to improve our understanding of severe mental disorders. FUNDING: Spanish National Research Agency (Agencia Estatal de Investigación, AEI) and the European Regional Development Fund, within the National Programme for Research Aimed at the Challenges of Society. Ref. FFI2017-86969-R (AEI/FEDER, UE). DURATION: 2018 – 2021