Papers › GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge

GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge

20 Aug 2019IJCNLP 2019 11arXiv:1908.07245archive 2025-07-28

Luyao Huang, Chi Sun, Xipeng Qiu, Xuanjing Huang

Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a particular context. Traditional supervised methods rarely take into consideration the lexical resources like WordNet, which are widely utilized in knowledge-based methods. Recent studies have shown the effectiveness of incorporating gloss (sense definition) into neural networks for WSD. However, compared with traditional word expert supervised methods, they have not achieved much improvement. In this paper, we focus on how to better leverage gloss knowledge in a supervised neural WSD system. We construct context-gloss pairs and propose three BERT-based models for WSD. We fine-tune the pre-trained BERT model on SemCor3.0 training corpus and the experimental results on several English all-words WSD benchmark datasets show that our approach outperforms the state-of-the-art systems.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

HSLCY/GlossBERT officialmentioned in papermentioned on GitHubpytorch report
nkhl-p/glossBERT mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Word Sense Disambiguation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Linking WiC-TSV GlossBert-ws Task 1 Accuracy: all 75.9 #3 of 8 Archive leaderboard report
Entity Linking WiC-TSV GlossBert-ws Task 1 Accuracy: domain specific 76.7 #3 of 8 Archive leaderboard report
Entity Linking WiC-TSV GlossBert-ws Task 1 Accuracy: general purpose 75.2 #3 of 8 Archive leaderboard report
Word Sense Disambiguation Supervised: GlossBERT SemEval 2007 72.5 #15 of 27 Archive leaderboard report
Word Sense Disambiguation Supervised: GlossBERT SemEval 2013 76.1 #15 of 27 Archive leaderboard report
Word Sense Disambiguation Supervised: GlossBERT SemEval 2015 80.4 #15 of 27 Archive leaderboard report
Word Sense Disambiguation Supervised: GlossBERT Senseval 2 77.7 #15 of 27 Archive leaderboard report
Word Sense Disambiguation Supervised: GlossBERT Senseval 3 75.2 #15 of 27 Archive leaderboard report
Word Sense Disambiguation WiC-TSV GlossBert-ws Task 1 Accuracy: all 75.9 #3 of 8 Archive leaderboard report
Word Sense Disambiguation WiC-TSV GlossBert-ws Task 1 Accuracy: domain specific 76.7 #3 of 8 Archive leaderboard report
Word Sense Disambiguation WiC-TSV GlossBert-ws Task 1 Accuracy: general purpose 75.2 #3 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections