A5006567976- Natural Language Processing Techniques
- Topic Modeling
- Semantic Web and Ontologies
- Lexicography and Language Studies
- Text Readability and Simplification
- Speech Recognition and Synthesis
- Authorship Attribution and Profiling
- Speech and dialogue systems
- linguistics and terminology studies
- Biomedical Text Mining and Ontologies
- Service-Oriented Architecture and Web Services
- COVID-19 Clinical Research Studies
- Syntax, Semantics, Linguistic Variation
- Mathematics, Computing, and Information Processing
- Time Series Analysis and Forecasting
- Speech and Audio Processing
- Gender Studies in Language
- Expert finding and Q&A systems
- Literature, Language, and Rhetoric Studies
- Adversarial Robustness in Machine Learning
- Web Data Mining and Analysis
- Second Language Acquisition and Learning
- Educational Tools and Methods
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
Romanian Academy
2015-2024
Artificial Intelligence Research Institute
2015-2023
Bulgarian Academy of Sciences
2023
Heinrich Heine University Düsseldorf
2023
University of New Hampshire
2023
University of New Hampshire at Manchester
2023
Charles University
2018
University of Pitesti
2014
Dimitrie Cantemir Christian University
2014
Transformer models produce advanced text representations that have been used to break through the hard challenge of natural language understanding. Using Transformer’s attention mechanism, which acts as a learning memory, trained on tens billions words, word sense disambiguation (WSD) algorithm can now construct more faithful vectorial representation context be disambiguated. Working with set 34 lemmas nouns, verbs, adjectives and adverbs selected from National Reference Corpus Romanian...
In an era when large amounts of data are generated daily in various fields, the biomedical field among others, linguistic resources can be exploited for tasks Natural Language Processing. Moreover, increasing number documents available languages other than English. To able to extract information from natural language free text resources, methods and tools needed a variety languages. This paper presents creation MoNERo corpus, gold standard corpus Romanian, annotated with both part speech...
“Multiword expressions” are groups of words acting as a morphologic, syntactic and semantic unit in linguistic analysis. Verbal multiword expressions represent the subgroup expressions, namely that which verb is head group considered its canonical (or dictionary) form. All great challenge for natural language processing, but verbal ones particularly interesting tasks such parsing, central element organization sentence. In this paper we introduce our data-driven approach to was objectively...
Multiword expressions (MWEs) are challenging and pervasive phenomena whose idiosyncratic properties show notably at the levels of lexicon, morphology, syntax. Thus, they should best be annotated jointly with morphosyntax. We discuss two multilingual initiatives, Universal Dependencies PARSEME, addressing these annotation layers in cross-lingually unified ways. compare principles initiatives respect to MWEs, we put forward a roadmap towards their gradual unification. The expected outcomes...
Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate performance mBERT model MWE identification a multilingual context by training it on all 14 languages available version 1.2 PARSEME corpus. We also incorporate lateral inhibition adversarial into our methodology to create language-independent embeddings...