mlsanityData to 7 Oct 2026

Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences

arXiv 2009.11795 ↗First posted 24 Sep 2020cs.CL cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, our models are able to achieve state-of-the-art results on the English all-words benchmark datasets.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 6; 2024: 1; 2025: 1.

14 papers.

Sort:

  1. 2021Modeling Event Plausibility with Consistent Conceptual Abstractioncited by 20
  2. 2022ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSDcited by 18
  3. 2023A Review of the Trends and Challenges in Adopting Natural Language Processing Methods for Education Feedback Analysiscited by 12
  4. 2023SALMA: Arabic Sense-Annotated Corpus and WSD Benchmarkscited by 10
  5. 2023What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventoriescited by 9
  6. 2023Context-Gloss Augmentation for Improving Arabic Target Sense Verificationcited by 6
  7. 2021Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventoriescited by 5
  8. 2022Language Models Are Poor Learners of Directional Inferencecited by 4
  9. 2023Word Sense Disambiguation as a Game of Neurosymbolic Dartscited by 3
  10. 2021Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measurescited by 2
  11. 2023ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedurecited by 2
  12. 2025PolyBERT: Fine-Tuned Poly Encoder BERT-Based Model for Word Sense Disambiguationcited by 1
2 more
  1. 2022Lost in Context? On the Sense-wise Variance of Contextualized Word Embeddingscited by 0
  2. 2024Word Sense Disambiguation in Native Spanish: A Comprehensive Lexical Evaluation Resourcecited by 0