Papers › Word Sense Disambiguation with Transformer Models

Word Sense Disambiguation with Transformer Models

30 Apr 2021SemDeep 2021 1archive 2025-07-28

Pierre-Yves Vandenbussche, Tony Scerri, Ron Daniel Jr.

In this paper, we tackle the task of Word Sense Disambiguation (WSD). We present our system submitted to the Word-in-Context Target Sense Verification challenge, part of the SemDeep workshop at IJCAI 2020 (Breit et al., 2020). That challenge asks participants to predict if a specific mention of a word in a text matches a pre-defined sense. Our approach uses pre-trained transformer models such as BERT that are fine-tuned on the task using different architecture strategies. Our model achieves the best accuracy and precision on Subtask 1 – make use of definitions for deciding whether the target word in context corresponds to the given sense or not. We believe the strategies we explored in the context of this challenge can be useful to other Natural Language Processing tasks.

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Entity LinkingWord Sense Disambiguation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Linking WiC-TSV transformers Task 1 Accuracy: all 77.8 #1 of 8 Archive leaderboard report
Entity Linking WiC-TSV transformers Task 1 Accuracy: domain specific 81.0 #1 of 8 Archive leaderboard report
Entity Linking WiC-TSV transformers Task 1 Accuracy: general purpose 75.2 #1 of 8 Archive leaderboard report
Entity Linking WiC-TSV transformers Task 3 Accuracy: all 71.9 #1 of 8 Archive leaderboard report
Entity Linking WiC-TSV transformers Task 3 Accuracy: domain specific 65.7 #1 of 8 Archive leaderboard report
Entity Linking WiC-TSV transformers Task 3 Accuracy: general purpose 77.0 #1 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