{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multilingual-knowledge-graph-embeddings-for","title":"Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment","arxiv_id":"1611.03954","date":"2016-11-12","proceeding":null,"authors":["Muhao Chen","Yingtao Tian","Mohan Yang","Carlo Zaniolo"],"abstract":"Many recent works have demonstrated the benefits of knowledge graph\nembeddings in completing monolingual knowledge graphs. Inasmuch as related\nknowledge bases are built in several different languages, achieving\ncross-lingual knowledge alignment will help people in constructing a coherent\nknowledge base, and assist machines in dealing with different expressions of\nentity relationships across diverse human languages. Unfortunately, achieving\nthis highly desirable crosslingual alignment by human labor is very costly and\nerrorprone. Thus, we propose MTransE, a translation-based model for\nmultilingual knowledge graph embeddings, to provide a simple and automated\nsolution. By encoding entities and relations of each language in a separated\nembedding space, MTransE provides transitions for each embedding vector to its\ncross-lingual counterparts in other spaces, while preserving the\nfunctionalities of monolingual embeddings. We deploy three different techniques\nto represent cross-lingual transitions, namely axis calibration, translation\nvectors, and linear transformations, and derive five variants for MTransE using\ndifferent loss functions. Our models can be trained on partially aligned\ngraphs, where just a small portion of triples are aligned with their\ncross-lingual counterparts. The experiments on cross-lingual entity matching\nand triple-wise alignment verification show promising results, with some\nvariants consistently outperforming others on different tasks. We also explore\nhow MTransE preserves the key properties of its monolingual counterpart TransE.","url_abs":"http://arxiv.org/abs/1611.03954v3","url_pdf":"http://arxiv.org/pdf/1611.03954v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multilingual-knowledge-graph-embeddings-for","repo_url":"https://github.com/muhaochen/MTransE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multilingual-knowledge-graph-embeddings-for","repo_url":"https://github.com/muhaochen/MTransE-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-alignment","task_name":"Entity Alignment"},{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"mtranse","method_name":"MTransE"},{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mtranse","name":"MTransE","full_name":"MTransE"}],"results":[{"leaderboard":"/sota/entity-alignment-on-dbp15k-zh-en","task":"Entity Alignment","dataset":"DBP15k zh-en","model":"MTransE","rank_in_archive_order":38,"of":38,"metrics":{"Hits@1":"0.308"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.03954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.03954"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/muhaochen/MTransE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/muhaochen/MTransE-tf","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"020f49ecea6b5347","entry":"random_orthogonal_matrix","repo":"muhaochen/MTransE","repo_kind":"listed","path":"src/common/utils.py","file_url":"https://github.com/muhaochen/MTransE/blob/HEAD/src/common/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"020f49ecea6b5347"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}