STORRE Collection: Electronic copies of Literature and Languages conference papers and proceedings.Electronic copies of Literature and Languages conference papers and proceedings.http://hdl.handle.net/1893/8212024-03-18T08:12:33Z2024-03-18T08:12:33ZMetaMap versus BERT models with explainable active learning: ontology-based experiments with prior knowledge for COVID-19Arguello-Casteleiro, MercedesHenson, CMaroto, NavaLi, SaihongDes-Diz, JulioFernandez-Prieto, Maria JesusPeters, SarahFurmston, TimSevillano Torrado, CarlosMaseda Fernandez, DiegoKulshrestha, MKeane, JohnStevens, RobertWroe, Chrishttp://hdl.handle.net/1893/343232022-05-14T00:05:15Z2022-01-01T00:00:00ZTitle: MetaMap versus BERT models with explainable active learning: ontology-based experiments with prior knowledge for COVID-19
Author(s): Arguello-Casteleiro, Mercedes; Henson, C; Maroto, Nava; Li, Saihong; Des-Diz, Julio; Fernandez-Prieto, Maria Jesus; Peters, Sarah; Furmston, Tim; Sevillano Torrado, Carlos; Maseda Fernandez, Diego; Kulshrestha, M; Keane, John; Stevens, Robert; Wroe, Chris
Abstract: Emergence of the Coronavirus 2019 Disease has highlighted further the need for timely support for clinicians as they manage severely ill patients. We combine Semantic Web technologies with Deep Learning for Natural Language Processing with the aim of converting human-readable best evi-dence/practice for COVID-19 into that which is computer-interpretable. We present the results of experiments with 1212 clinical ideas (medical terms and expressions) from two UK national healthcare services specialty guides for COVID-19 and three versions of two BMJ Best Practice documents for COVID-19. The paper seeks to recognise and categorise clinical ideas, performing a Named Entity Recognition (NER) task, with an ontology providing extra terms as context and describing the intended meaning of categories understandable by clinicians. The paper investigates: 1) the performance of classical NER using MetaMap versus NER with fine-tuned BERT models; 2) the integration of both NER approaches using a lightweight ontology developed in close collaboration with senior doctors; and 3) the easy interpretation by junior doctors of the main classes from the ontology once populated with NER results. We report the NER performance and the observed agreement for human audits.2022-01-01T00:00:00ZViolences, stratégies adaptatives et résiliences: le cas du RwandaGrayson, Hannahhttp://hdl.handle.net/1893/312122021-04-23T07:12:26Z2020-01-01T00:00:00ZTitle: Violences, stratégies adaptatives et résiliences: le cas du Rwanda
Author(s): Grayson, Hannah
Editor(s): Mazurek, Hubert
Abstract: The genocide against the Tutsi destroyed the social fabric of Rwanda, and its traumatic and violent consequences have received much attention amongst researchers. Yet less attention has been paid to stories of positive change. Alongside reconciliation at a national level, individual stories of resilience have emerged. This contribution aims to move beyond the dominant narratives of the genocide by examining the themes of resilience and post-traumatic growth in the contemporary testimonies of Rwandans.2020-01-01T00:00:00ZStable communication through dynamic languageSmith, Andrew D Mhttp://hdl.handle.net/1893/91182021-05-10T00:31:48Z2005-01-01T00:00:00ZTitle: Stable communication through dynamic language
Author(s): Smith, Andrew D M
Abstract: I use agent-based computational models of inferential language transmission to investigate the relationship between language change and the indeterminacy of meaning. I describe a model of communication and learning based on the inference of meaning through disambiguation across multiple contexts, which is then embedded within an iterated learning model. The dynamic flexibility and uncertainty inherent in the model leads directly to variation between agents, in both their conceptual and lexical structures. Over generations of repeated meaning inference, this variation leads to significant language change. Despite such change, however, the language maintains its utility as a communicative tool within each individual generation.2005-01-01T00:00:00ZThe Pragmatics of Dreams in James Hogg’s ‘Cousin Mattie’Leonardi, Barbarahttp://hdl.handle.net/1893/216382021-04-30T17:25:35Z2012-01-01T00:00:00ZTitle: The Pragmatics of Dreams in James Hogg’s ‘Cousin Mattie’
Author(s): Leonardi, Barbara
Abstract: Scottish writer James Hogg (1770-1835) made highly sophisticated use of the supernatural in his realist works. Though judged as a 'childish' and a 'naïve' writer by contemporary reviewers, Hogg exploited the possibilities offered by the Scottish Borders' tradition for his narratorial purposes, in so doing conveying subtle critiques of contemporary social issues outwith the text. In 'Cousin Mattie' (1820) Hogg employed the superstitious belief in foretelling dreams and the fairies' magic number of seven to construct the plot of his tale. Through flouting Grice's 'maxims' of 'quantity' and 'manner' with a highly ambiguous ending, the 'maxim of quality' by a strategic use of the supernatural, and by intertextually referencing contemporary ballads of infanticide, Hogg exposed the social stigmatization of unwed mothers and the harsh reality of life in rural Scotland. Ambiguity concerning the reasons of Mattie's death made more acceptable an issue deemed 'indelicate' to nineteenth-century bourgeois readers, whom Hogg left to discern symbolic meanings, avoiding threatening their assumptions of literary politeness, and leaving the possibility of different interpretations, neither of which excludes the other.2012-01-01T00:00:00Z