A5035746903- Natural Language Processing Techniques
- Text Readability and Simplification
- Topic Modeling
- Health, Environment, Cognitive Aging
- Biomedical Text Mining and Ontologies
- Interpreting and Communication in Healthcare
- Semantic Web and Ontologies
- Genetics, Bioinformatics, and Biomedical Research
- Software Engineering Research
- Sentiment Analysis and Opinion Mining
- Misinformation and Its Impacts
- Advanced Text Analysis Techniques
- Software Engineering Techniques and Practices
- Authorship Attribution and Profiling
- Explainable Artificial Intelligence (XAI)
- Wikis in Education and Collaboration
- Ethics and Social Impacts of AI
- Multimodal Machine Learning Applications
- Artificial Intelligence in Healthcare and Education
- Spam and Phishing Detection
- Advanced Malware Detection Techniques
- Computational and Text Analysis Methods
- Emergency and Acute Care Studies
- Digital Communication and Language
- Pharmacovigilance and Adverse Drug Reactions
Manchester Metropolitan University
2018-2025
IT University of Copenhagen
2023
Tokyo Institute of Technology
2023
Administration for Community Living
2023
American Jewish Committee
2023
University of Manchester
2013-2018
Open Text (Canada)
2016-2018
Buglife
2006
Summary Evidence‐based policy requires researchers to provide the answers ecological questions that are of interest makers. To find out what those in UK, representatives from 28 organizations involved policy, together with scientists 10 academic institutions, were asked generate a list their organizations. During 2‐day workshop initial 1003 generated consulting at least 654 makers and academics was used as basis for generating short 100 significant relevance. Short‐listing decided on...
Text simplification modifies syntax and lexicon to improve the understandability of language for an end user. This survey identifies classifies research within period 1998-2013. Simplification can be used many applications, including: Second learners, preprocessing in pipelines assistive technology. There are approaches task, lexical, syntactic, statistical machine translation hybrid techniques. also explores current challenges which this field faces. is a non-trivial task rapidly growing...
The abundance of text available in social media and health related forums along with the rich expression public opinion have recently attracted interest community to use these sources for pharmacovigilance. Based on intuition that patients post about Adverse Drug Reactions (ADRs) expressing negative sentiments, we investigate effect sentiment analysis features locating ADR mentions. We enrich feature space a state-of-the-art identification method features. Using corpus posts from...
This paper presents the results and main findings of SemEval-2021 Task 1 - Lexical Complexity Prediction. We provided participants with an augmented version CompLex Corpus (Shardlow et al. 2020). is English multi-domain corpus in which words multi-word expressions (MWEs) were annotated respect to their complexity using a five point Likert scale. featured two Sub-tasks: Sub-task focused on single 2 MWEs. The competition attracted 198 teams total, 54 submitted official runs test data 37 2.
Text mining (TM) methods have been used extensively to extract relations and events from the literature. In addition, TM techniques various types or dimensions of interpretative information, known as Meta-Knowledge (MK), context events, e.g. negation, speculation, certainty knowledge type. However, most existing focussed on extraction individual MK, without investigating how they can be combined obtain even richer contextual information. this paper, we describe a novel, supervised method new...
Students’ evaluation of teaching, for instance, through feedback surveys, constitutes an integral mechanism quality assurance and enhancement teaching learning in higher education. These surveys usually comprise both the Likert scale free-text responses. Since discrete responses are easy to analyze, they feature more prominently survey analyses. However, often contain richer, detailed, nuanced information with actionable insights. Mining these insights is challenging, as it requires a degree...
Abstract Lexical Simplification (LS) is the task of substituting complex words within a sentence for simpler alternatives while maintaining sentence’s original meaning. LS lexical component Text (TS) systems with aim improving accessibility to various target populations such as individuals low literacy or reading disabilities. Prior surveys have been published several years before introduction transformers, transformer-based large language models (LLMs), and prompt learning that drastically...
Recent studies of social media have made a unanimous conclusion that public opinions can be altered through systematic exploitation using bot accounts. The existing detection methodologies utilize features the accounts to label them as either or human. However, in this work, we propose convolutional neural network (CNN) identify single post on media. We compared our results with an artificial (ANN) trained extracted from accounts' profiles. Results shown detected 98.71% accuracy CNN 97.6%...
Predicting which words are considered hard to understand for a given target population is vital step in many NLP applications such as text simplification. This task commonly referred Complex Word Identification (CWI). With few exceptions, previous studies have approached the binary classification systems predict complexity value (complex vs. non-complex) set of text. choice motivated by fact that all CWI datasets compiled so far been annotated using annotation scheme. Our paper addresses...
Even in highly-developed countries, as many 15-30% of the population can only understand texts written using a basic vocabulary. Their understanding everyday is limited, which prevents them from taking an active role society and making informed decisions regarding healthcare, legal representation, or democratic choice. Lexical simplification natural language processing task that aims to make text understandable everyone by replacing complex vocabulary expressions with simpler ones, while...
Horacio Saggion, Sanja Štajner, Daniel Ferrés, Kim Cheng Sheang, Matthew Shardlow, Kai North, Marcos Zampieri. Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022). 2022.
<title>Abstract</title> Background Effective communication is essential for delivering quality healthcare, particularly individuals with Functional Neurological Disorders (FND), who are often subject to misdiagnosis and stigmatising language that implies symptom fabrication. Variability in styles among healthcare professionals may contribute these challenges, affecting patient understanding care outcomes. Methods This study employed natural processing (NLP) analyse clinician-to-clinician...
Clinical letters are infamously impenetrable for the lay patient. This work uses neural text simplification methods to automatically improve understandability of clinical patients. We take existing software and augment it with a new phrase table that links complex medical terminology simpler vocabulary by mining SNOMED-CT. In an evaluation task using crowdsourcing, we show results our system ranked easier understand (average rank 1.93) than original (2.34) without table. also improvement...
Abstract The digitisation of higher education is raising significant questions about the impact artificial intelligence and automation on teaching learning environments, highlighting need to investigate how teachers students can work with new educational technologies in complementary ways. This paper reports results from a pilot study collaborative augmentation simplification text (CoAST) system, which online software designed facilitate engagement university theoretically-sophisticated...
In this work, we uncover a hidden linguistic property of emoji, namely that they are polysemous and can be used to form semantic network emoji meanings. Our key contributions direction study as follows: (1) We have developed new corpus help in the task sense prediction. This contains tweets with single emojis, where each has been labelled an appropriate identifier from WordNet. (2) Experiments, which demonstrate it is possible predict using our reasonable level accuracy. able report average...
Abstract Urdu is morphologically rich language and lacks the resources available in English. While several studies on image captioning task English have been published, this among pioneer generative captioning. The study makes key contributions: (i) it presents a new dataset for captioning, (ii) different attention-based architectures language. These attention mechanisms are to language, as those never used (iii) Finally, performs quantitative qualitative analysis of results by studying...
Tomas Goldsack, Zheheng Luo, Qianqian Xie, Carolina Scarton, Matthew Shardlow, Sophia Ananiadou, Chenghua Lin. The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks. 2023.