A5011442841- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Topic Modeling
- linguistics and terminology studies
- Biomedical Text Mining and Ontologies
- Language, Metaphor, and Cognition
- Gender Studies in Language
- Advanced Text Analysis Techniques
- Linguistic research and analysis
- Lexicography and Language Studies
- Multimodal Machine Learning Applications
- Intelligent Tutoring Systems and Adaptive Learning
- Constraint Satisfaction and Optimization
- Neural Networks and Applications
- Advanced Graph Neural Networks
- Speech and dialogue systems
- Action Observation and Synchronization
- Service-Oriented Architecture and Web Services
- Hate Speech and Cyberbullying Detection
- Image Retrieval and Classification Techniques
- Complex Network Analysis Techniques
- Cognitive Science and Education Research
- Reinforcement Learning in Robotics
- Impact of AI and Big Data on Business and Society
- Swearing, Euphemism, Multilingualism
University of Vienna
2019-2025
The London College
2023
Center for Applied Linguistics
2021
Bar-Ilan University
2021
University of Helsinki
2021
Tel Aviv University
2021
Technical University of Darmstadt
2021
University of Copenhagen
2021
Edinburgh Napier University
2021
Universitat Pompeu Fabra
2021
Automated Term Extraction (ATE), even though well-investigated, continues to be a challenging task.Approaches conventionally extract terms on corpus or document level and the benefits of neural models still remain underexplored with very few exceptions.We introduce three transformer-based term extraction operating sentence level: language model for token classification, one sequence an innovative use Neural Machine Translation (NMT), which learns reduce sentences terms.All are trained tested...
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, barriers impacting business, cross-lingual cross-cultural communication are still omnipresent. Language Technologies (LTs) powerful means to break down these barriers. While last decade has seen various initiatives that created multitude approaches technologies tailored Europe's specific needs, there an immense level fragmentation. At same time, AI...
Limited accessibility to language resources and technologies represents a challenge for the analysis, preservation, documentation of natural languages other than English. Linguistic Linked (Open) Data (LLOD) holds promise ease creation, linking, reuse multilingual linguistic data across distributed heterogeneous resources. However, individual accommodate or target different description levels, e.g., morphology, syntax, phonology, pragmatics. In this comprehensive survey, state-of-the-art...
SPARQL is a highly powerful query language for an ever-growing number of Linked Data resources and Knowledge Graphs. Using it requires certain familiarity with the entities in domain to be queried as well expertise language's syntax semantics, none which average human web users can assumed possess. To overcome this limitation, automatically translating natural questions queries has been vibrant field research. However, date, vast success deep learning methods not yet fully propagated...
Conceptual metaphors present a powerful cognitive vehicle to transfer knowledge structures from source target domain. Prior neural approaches focus on detecting whether natural language sequences are metaphoric or literal. We believe that truly probe in pre-trained models, their capability detect this should be investigated. To end, paper proposes the ability of GPT-3 and predict metaphor's domain without any pre-set domains. experiment with different training sample configurations for...
Investigating dictionary use is not only essential to the process of compilation and evaluation but equally establishing a best practice strategic consultation. User research past few decades has tended focus either on pedagogical lexicography or specific lexicographic resources. In particular, proportion investigations in specialised settings seems comparatively low. order redress balance, present study evaluates resource selection consultation strategies 430 L2 learners five languages...
In the cognitive sciences, image schemas are considered to be conceptual building blocks learned from sensorimotor processes in early infancy. They used language and higher levels of cognition as information skeletons. Despite potential integrating into formal systems aid for instance common-sense reasoning, computational analogy concept invention, normalisations sparse. particular respect their dynamic nature. this paper, we therefore describe how some aspects schema Containment can...
A vision of a truly multilingual Semantic Web has found strong support with the Linguistic Linked Open Data community. Standards, such as OntoLex-Lemon, highlight importance explicit linguistic modeling in relation to ontologies and knowledge graphs. Nevertheless, there is room for improveme nt terms automation, usability, interoperability. Neural Language Models have achieved several breakthroughs successes considerably beyond Natural Processing (NLP) tasks recently also multimodal...
Games have always been a popular domain of AI research, and they used for many recent competitions. Reaching human‐level performance, however, often either focuses on comprehensive world knowledge or solving decision‐making problems with unmanageable solution spaces. Building the Taboo board game, Challenge Competition addresses different problem — that bridging gap between heterogeneous agents trying to jointly identify concept without making reference its most salient features. The...
Commonsense knowledge is a broad and challenging area of research which investigates our understanding the world as well human assumptions about reality. Deriving directly from subjective perception external world, it intrinsically intertwined with embodied cognition. reasoning linked to sense-making, pattern recognition framing abilities. This work presents new resource that formalizes cognitive theory image schemas. Image schemas are dynamic conceptual building blocks originating...
Numerous success use cases involving deep learning have recently started to be propagated the Semantic Web.Approaches range from utilizing structured knowledge in training process of neural networks enriching such architectures with ontological reasoning mechanisms.Bridging neural-symbolic gap by joining and Web not only holds potential improving performance but also opening up new avenues research.This editorial introduces Journal special issue on Deep Learning, which brings together...
Rich data provided by tweets have been analyzed, clustered, and explored in a variety of studies.Typically those studies focus on named entity recognition, linking, disambiguation or clustering.Tweets hashtags are generally analyzed sentential word level but not compositional concatenated words.We propose an approach for closer analysis compounds hashtags, the long run also other types text sequences tweets, order to enhance clustering such documents.Hashtags used before as primary topic...