Papers › Joint Language Semantic and Structure Embedding for Knowledge Graph Completion
Joint Language Semantic and Structure Embedding for Knowledge Graph Completion
Jianhao Shen, Chenguang Wang, Linyuan Gong, Dawn Song
The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike previous approaches that rely on either the structures or semantics of the knowledge graphs, we propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models with respect to a probabilistic structured loss, where the forward pass of the language models captures semantics and the loss reconstructs structures. Our extensive experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method. We also show that our method can significantly improve the performance in a low-resource regime, thanks to the better use of semantics. The code and datasets are available at https://github.com/pkusjh/LASS.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Prediction | FB15k-237 | LASS | Hits@10 | 0.533 | #62 of 75 | Archive leaderboard | report |
| Link Prediction | FB15k-237 | LASS | MR | 108 | #62 of 75 | Archive leaderboard | report |
| Link Prediction | UMLS | LASS | Hits@10 | 0.994 | #3 of 10 | Archive leaderboard | report |
| Link Prediction | UMLS | LASS | MR | 1.39 | #3 of 10 | Archive leaderboard | report |
| Link Prediction | WN18RR | LASS | Hits@10 | 0.786 | #6 of 75 | Archive leaderboard | report |
| Link Prediction | WN18RR | LASS | MR | 35 | #6 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.
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