Papers › MLMLM: Link Prediction with Mean Likelihood Masked Language Model
MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Louis Clouatre, Philippe Trempe, Amal Zouaq, Sarath Chandar
Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. They however scale with man-hours and high-quality data. Masked Language Models (MLMs), such as BERT, scale with computing power as well as unstructured raw text data. The knowledge contained within those models is however not directly interpretable. We propose to perform link prediction with MLMs to address both the KBs scalability issues and the MLMs interpretability issues. To do that we introduce MLMLM, Mean Likelihood Masked Language Model, an approach comparing the mean likelihood of generating the different entities to perform link prediction in a tractable manner. We obtain State of the Art (SotA) results on the WN18RR dataset and the best non-entity-embedding based results on the FB15k-237 dataset. We also obtain convincing results on link prediction on previously unseen entities, making MLMLM a suitable approach to introducing new entities to a KB.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2009.07058", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2009.07058")
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Prediction | FB15k-237 | MLMLM | Hits@1 | 0.1871 | #53 of 75 | Archive leaderboard | report |
| Link Prediction | FB15k-237 | MLMLM | Hits@10 | 0.4026 | #53 of 75 | Archive leaderboard | report |
| Link Prediction | FB15k-237 | MLMLM | Hits@3 | 0.2820 | #53 of 75 | Archive leaderboard | report |
| Link Prediction | FB15k-237 | MLMLM | MR | 411 | #53 of 75 | Archive leaderboard | report |
| Link Prediction | FB15k-237 | MLMLM | MRR | 0.2591 | #53 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | MLMLM | Hits@1 | 0.4391 | #14 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | MLMLM | Hits@10 | 0.611 | #14 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | MLMLM | Hits@3 | 0.5418 | #14 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | MLMLM | MR | 1603 | #14 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | MLMLM | MRR | 0.5017 | #14 of 75 | 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
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