Papers › CTLR@WiC-TSV: Target Sense Verification using Marked Inputs andPre-trained Models

CTLR@WiC-TSV: Target Sense Verification using Marked Inputs andPre-trained Models

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

José G. Moreno, Elvys Linhares Pontes, Gaël Dias

This paper describes the CTRL participation in the Target Sense Verification of the Words in Context challenge (WiC-TSV) at SemDeep6. Our strategy is based on a simplistic annotation scheme of the target words to later be classified by well-known pre-trained neural models. In particular, the marker allows to include position information to help models to correctly identify the word to disambiguate. Results on the challenge show that our strategy outperforms other participants (+11, 4 Accuracy points) and strong baselines (+1, 7 Accuracy points).

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 Linking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Linking WiC-TSV CTLR Task 1 Accuracy: all 76.8 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 1 Accuracy: domain specific 79.6 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 1 Accuracy: general purpose 74.5 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 2 Accuracy: all 72.7 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 2 Accuracy: domain specific 81.5 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 2 Accuracy: general purpose 65.6 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 3 Accuracy: all 78.3 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 3 Accuracy: domain specific 85.7 #2 of 8 Archive leaderboard report
Entity Linking WiC-TSV CTLR Task 3 Accuracy: general purpose 72.1 #2 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

AdaGradAttentionBPECTRLDense ConnectionsDropoutGradient ClippingLayer NormalizationLinear LayerLinear WarmupMulti-Head AttentionReLUResidual ConnectionSoftmax

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