Papers › SenseBERT: Driving Some Sense into BERT

SenseBERT: Driving Some Sense into BERT

15 Aug 2019ACL 2020 6arXiv:1908.05646archive 2025-07-28

Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham

The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a surrogate for the underlying semantic content. This paper proposes a method to employ weak-supervision directly at the word sense level. Our model, named SenseBERT, is pre-trained to predict not only the masked words but also their WordNet supersenses. Accordingly, we attain a lexical-semantic level language model, without the use of human annotation. SenseBERT achieves significantly improved lexical understanding, as we demonstrate by experimenting on SemEval Word Sense Disambiguation, and by attaining a state of the art result on the Word in Context task.

PaperPDFConference PDF

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

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

Language ModelingLanguage ModellingNatural Language InferenceNatural Language UnderstandingWord Sense Disambiguation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference QNLI SenseBERT-base 110M Accuracy 90.6% #33 of 43 Archive leaderboard report
Natural Language Inference RTE SenseBERT-base 110M Accuracy 67.5% #62 of 90 Archive leaderboard report
Word Sense Disambiguation Words in Context SenseBERT-large 340M Accuracy 72.1 #11 of 37 Archive leaderboard report
Word Sense Disambiguation Words in Context SenseBERT-base 110M Accuracy 70.3 #12 of 37 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.

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