Results 1 to 10 of about 54,181 (112)
Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training.
Terra Blevins, Luke Zettlemoyer
semanticscholar +1 more source
Multilingual Word Sense Disambiguation with Unified Sense Representation [PDF]
International Conference on Computational Linguistics, 2022 As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the fine-grained semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD systems have
Ying Su +3 more
semanticscholar +1 more source
SemEval-2023 Task 1: Visual Word Sense Disambiguation
International Workshop on Semantic Evaluation, 2023 This paper presents the Visual Word Sense Disambiguation (Visual-WSD) task.The objective of Visual-WSD is to identify among a set of ten images the one that corresponds to the intended meaning of a given ambiguous word which is accompanied with minimal ...
Alessandro Raganato +4 more
semanticscholar +1 more source
Recent Trends in Word Sense Disambiguation: A Survey
International Joint Conference on Artificial Intelligence, 2021 Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word in context by identifying the most suitable meaning from a predefined sense inventory.
Michele Bevilacqua +3 more
semanticscholar +1 more source
XL-WSD: An Extra-Large and Cross-Lingual Evaluation Framework for Word Sense Disambiguation
AAAI Conference on Artificial Intelligence, 2021 Transformer-based architectures brought a breeze of change to Word Sense Disambiguation (WSD), improving models' performances by a large margin. The fast development of new approaches has been further encouraged by a well-framed evaluation suite for ...
Tommaso Pasini +2 more
semanticscholar +1 more source
Nibbling at the Hard Core of Word Sense Disambiguation
Annual Meeting of the Association for Computational Linguistics, 2022 With state-of-the-art systems having finally attained estimated human performance, Word Sense Disambiguation (WSD) has now joined the array of Natural Language Processing tasks that have seemingly been solved, thanks to the vast amounts of knowledge ...
Marco Maru +3 more
semanticscholar +1 more source
Analysis and Evaluation of Language Models for Word Sense Disambiguation
International Conference on Computational Logic, 2021 Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in capturing context ...
Daniel Loureiro +3 more
semanticscholar +1 more source
Determining the difficulty of Word Sense Disambiguation [PDF]
Journal of Biomedical Informatics, 2014 Automatic processing of biomedical documents is made difficult by the fact that many of the terms they contain are ambiguous. Word Sense Disambiguation (WSD) systems attempt to resolve these ambiguities and identify the correct meaning. However, the published literature on WSD systems for biomedical documents report considerable differences in ...
McInnes, Bridget T., Stevenson, Mark
openaire +2 more sources
ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension
Conference on Empirical Methods in Natural Language Processing, 2021 Supervised systems have nowadays become the standard recipe for Word Sense Disambiguation (WSD), with Transformer-based language models as their primary ingredient.
Edoardo Barba +2 more
semanticscholar +1 more source
FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2021 Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics. This stems from a lack of data for both modeling and evaluating rare senses in existing WSD datasets.
Terra Blevins +2 more
semanticscholar +1 more source