Contrastive Learning for Morphological Disambiguation Using Large Language Models in Low-Resource Settings [PDF]
Applied SciencesIn this paper, a contrastive learning approach for morphological disambiguation (MD) using large language models (LLMs) is presented. A contrastive loss function is introduced for training the approach, which reduces the distance between the correct ...
Gulmira Tolegen +2 more
doaj +4 more sources
Minimalist Entity Disambiguation for Mid-Resource Languages [PDF]
Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), 2023 ,
Benno Kruit
semanticscholar +4 more sources
Unsupervised Named Entity Disambiguation for Low Resource Domains [PDF]
Proceedings of the 2024 Conference on Empirical Methods in Natural Language ProcessingIn the ever-evolving landscape of natural language processing and information retrieval, the need for robust and domain-specific entity linking algorithms has become increasingly apparent.
D. V. Datta, Soumajit Pramanik
semanticscholar +6 more sources
Hybrid Transformer-Based Large Language Models for Word Sense Disambiguation in the Low-Resource Sesotho sa Leboa Language [PDF]
Applied SciencesThis study addresses a lexical ambiguity issue in Sesotho sa Leboa that arises from terms with various meanings, often known as homonyms or polysemous words.
Hlaudi Daniel Masethe +4 more
doaj +3 more sources
Exploiting a lexical resource for discourse connective disambiguation in German [PDF]
Proceedings of the 28th International Conference on Computational Linguistics, 2020 In this paper we focus on connective identification and sense classification for explicit discourse relations in German, as two individual sub-tasks of the overarching Shallow Discourse Parsing task.
Peter Bourgonje, Manfred Stede
semanticscholar +3 more sources
Word Sense Disambiguation in Native Spanish: A Comprehensive Lexical Evaluation Resource [PDF]
arXiv.orgHuman language, while aimed at conveying meaning, inherently carries ambiguity. It poses challenges for speech and language processing, but also serves crucial communicative functions.
Pablo Ortega +4 more
semanticscholar +4 more sources
Data sets for author name disambiguation: an empirical analysis and a new resource [PDF]
Scientometrics, 2017 Data sets of publication meta data with manually disambiguated author names play an important role in current author name disambiguation (AND) research.
Mark-Christoph Müller +2 more
semanticscholar +5 more sources
Word Sense Disambiguation for Morphologically Rich Low-Resourced Languages: A Systematic Literature Review and Meta-Analysis [PDF]
InformationIn natural language processing, word sense disambiguation (WSD) continues to be a major difficulty, especially for low-resource languages where linguistic variation and a lack of data make model training and evaluation more difficult.
Hlaudi Daniel Masethe +4 more
doaj +3 more sources
A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis [PDF]
arXiv.orgIn-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios.
Mu, Wenxuan +3 more
semanticscholar +3 more sources
Hybrid artificial intelligence architectures for automatic text correction in the Kazakh language [PDF]
Frontiers in Artificial IntelligenceThe Kazakh language, as an agglutinative and morphologically rich language, presents significant challenges for the development of natural language processing (NLP) tools.
Laura Baitenova +4 more
doaj +2 more sources