A5058785189- Natural Language Processing Techniques
- Topic Modeling
- Lexicography and Language Studies
- Semantic Web and Ontologies
- Linguistic Variation and Morphology
- Software Engineering Research
- Linguistics, Language Diversity, and Identity
- Advanced Text Analysis Techniques
- Second Language Acquisition and Learning
- Authorship Attribution and Profiling
- Geographic Information Systems Studies
- Sentiment Analysis and Opinion Mining
- linguistics and terminology studies
- Misinformation and Its Impacts
- Stock Market Forecasting Methods
- Digital Communication and Language
- Translation Studies and Practices
- Text Readability and Simplification
- Language, Metaphor, and Cognition
- Auditing, Earnings Management, Governance
- Speech and dialogue systems
- Software Engineering Techniques and Practices
- Digital Mental Health Interventions
- Biomedical Text Mining and Ontologies
- Advanced Software Engineering Methodologies
Lancaster University
2016-2025
Centre for Mental Health
2021
Institute for Health Metrics and Evaluation
2021
Johns Hopkins University
2021
King Saud University
2021
Mental Health Research UK
2021
University of Birmingham
2018
University of California, Irvine
2016
The Open University
2015
University of Salento
2015
This paper reports the extension of key words method for comparison corpora. Using automatic tagging software that assigns part-of-speech and semantic field (domain) tags, a is described which permits extraction domains by applying keyness calculation to tag frequency lists. The combination methods shown allow macroscopic analysis (the study characteristics whole texts or varieties language) inform microscopic level (focussing on use particular linguistic feature) thereby suggesting those...
This paper describes a method of comparing corpora which uses frequency profiling. The can be used to discover key words in the differentiate one corpus from another. Using annotated corpora, it applied grammatical or word-sense categories. as quick way find differences between and is shown have applications study social differentiation use English vocabulary, profiling learner document analysis software engineering process.
To compare the frequencies with which patients cancer and health professionals use Violence Journey metaphors when writing online; to investigate of these by cancer, in view critiques war-related for adoption notion 'cancer journey' UK policy documents.Computer-assisted quantitative qualitative study two data sets totalling 753 302 words.A UK-based online forum (500 134 words) a website (253 168 words).56 between 2007 2012; 307 2008 2013.Patients both approximately 1.5 times per 1000 words...
Abstract We take a step towards addressing the under- representation of African continent in NLP research by bringing together different stakeholders to create first large, publicly available, high-quality dataset for named entity recognition (NER) ten languages. detail characteristics these languages help researchers and practitioners better understand challenges they pose NER tasks. analyze our datasets conduct an extensive empirical evaluation state- of-the-art methods across both...
In this article, we undertake selective quantitative analyses of the demographi-cally-sampled spoken English component British National Corpus (for brevity, referred to here as ''Conversational Corpus"). This is a subcorpus c. 4.5 million words, in which speakers and respondents (see I below) are identified by such factors gender, age, social group, geographical region. Using corpus analysis tool developed at Lancaster, comparison vocabulary speakers, highlighting those differences marked...
The dynamic changes in the composition, dry weight, and mineral nutrient status of heath following fire have been investigated. overall growth (dry weightltime) curve for aerial organs is essentially exponential. Soil moisture conserved by burning and, provided climatic conditions are favourable, regeneration all species rapid. Annual rare found only first year after a fire. Many fire-resistant regenerate rapidly from buriedperennating buds; others reproduce great numbers seeds. number...
Abstract We critically assess mainstream accounting and finance research applying methods from computational linguistics (CL) to study financial discourse. also review common themes innovations in the literature incremental contributions of studies CL over manual content analysis. Key conclusions emerging our analysis are: (a) is behind curve terms generally word sense disambiguation particular; (b) implementation issues mean proposed benefits are often less pronounced than proponents...
This study combines quantitative semi-automated corpus methods with manual qualitative analysis to investigate the use of Violence metaphors for cancer and end life in a 1,500,000-word data from three stakeholder groups healthcare: patients, family carers healthcare professionals. general, especially military metaphors, are conventionally used talk about illness, particularly cancer. However, they have also been criticized their potentially negative implications. The innovative methodology...
Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.
This paper presents the ParlaMint corpora containing transcriptions of sessions 17 European national parliaments with half a billion words. The are uniformly encoded, contain rich meta-data about 11 thousand speakers, and linguistically annotated following Universal Dependencies formalism named entities. Samples conversion scripts available from project's GitHub repository, complete openly via CLARIN.SI repository for download, as well through NoSketch Engine KonText concordancers Parlameter...
In this paper, we discuss the limitations of current syntactic composition mechanisms in aspect-oriented requirements engineering (AORE). We highlight that such not only increase coupling between aspects and base concerns but are also insufficient to capture intentionality aspect composition. Furthermore, they force engineer reason about semantic influences trade-offs among from a perspective. present description language (RDL) enriches existing natural specification with information derived...
Domain analysis involves not only looking at standard requirements documents (e.g., use case specifications) but also customer information packs, market analyses, etc. Looking across all these and deriving, in a practical scalable way, feature model that is comprised of coherent abstractions fundamental non-trivial challenge. We conduct an exploratory study to investigate the suitability Information Retrieval (IR) techniques for identification commonalities variabilities requirement...
A survey of the literature on distribution sclerophyllous understorey in Australia leads to conclusion that, although climatic conditions under which it grows may vary considerably, soils flourishes are always acid and very low available phosphorus nitrogen sometimes potassium, copper, zinc, molybdenum. The problem is how species able flourish such deficient soils. To provide a background for investigation this problem, detailed ecological study was initiated an extensive stand heath...