{"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/inductive-entity-representations-from-text","title":"Inductive Entity Representations from Text via Link Prediction","arxiv_id":"2010.03496","date":"2020-10-07","proceeding":null,"authors":["Daniel Daza","Michael Cochez","Paul Groth"],"abstract":"Knowledge Graphs (KG) are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation. Regardless of whether they are built manually by domain experts or with automatic pipelines, KGs are often incomplete. Recent work has begun to explore the use of textual descriptions available in knowledge graphs to learn vector representations of entities in order to preform link prediction. However, the extent to which these representations learned for link prediction generalize to other tasks is unclear. This is important given the cost of learning such representations. Ideally, we would prefer representations that do not need to be trained again when transferring to a different task, while retaining reasonable performance. In this work, we propose a holistic evaluation protocol for entity representations learned via a link prediction objective. We consider the inductive link prediction and entity classification tasks, which involve entities not seen during training. We also consider an information retrieval task for entity-oriented search. We evaluate an architecture based on a pretrained language model, that exhibits strong generalization to entities not observed during training, and outperforms related state-of-the-art methods (22% MRR improvement in link prediction on average). We further provide evidence that the learned representations transfer well to other tasks without fine-tuning. In the entity classification task we obtain an average improvement of 16% in accuracy compared with baselines that also employ pre-trained models. In the information retrieval task, we obtain significant improvements of up to 8.8% in NDCG@10 for natural language queries. We thus show that the learned representations are not limited KG-specific tasks, and have greater generalization properties than evaluated in previous work.","url_abs":"https://arxiv.org/abs/2010.03496v3","url_pdf":"https://arxiv.org/pdf/2010.03496v3.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":"inductive-entity-representations-from-text","repo_url":"https://github.com/dfdazac/blp","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"inductive-entity-representations-from-text","repo_url":"https://github.com/raphaelsty/mkb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"inductive-link-prediction","task_name":"Inductive Link Prediction"},{"task_slug":"inductive-knowledge-graph-completion","task_name":"Inductive knowledge graph completion"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/inductive-knowledge-graph-completion-on-fb15k","task":"Inductive knowledge graph completion","dataset":"FB15k-237-ind","model":"BLP-TransE","rank_in_archive_order":1,"of":1,"metrics":{"Hit@1":"0.113","Hits@10":"0.363","Hits@3":"0.213","MRR":"0.195"},"uses_additional_data":false},{"leaderboard":"/sota/inductive-knowledge-graph-completion-on","task":"Inductive knowledge graph completion","dataset":"WN18RR-ind","model":"BLP-TransE","rank_in_archive_order":1,"of":2,"metrics":{"Hit@10":"0.58","Hits@3":"0.361","MRR":"0.285"},"uses_additional_data":false},{"leaderboard":"/sota/inductive-knowledge-graph-completion-on","task":"Inductive knowledge graph completion","dataset":"WN18RR-ind","model":"BLP-ComplEx","rank_in_archive_order":2,"of":2,"metrics":{"Hits@1":"0.156"},"uses_additional_data":false},{"leaderboard":"/sota/inductive-knowledge-graph-completion-on-1","task":"Inductive knowledge graph completion","dataset":"Wikidata5m-ind","model":"BLP-SimplE","rank_in_archive_order":1,"of":3,"metrics":{"Hits@1":"0.289","MRR":"0.493"},"uses_additional_data":false},{"leaderboard":"/sota/inductive-knowledge-graph-completion-on-1","task":"Inductive knowledge graph completion","dataset":"Wikidata5m-ind","model":"BLP-ComplEx","rank_in_archive_order":3,"of":3,"metrics":{"Hits@10":"0.877","Hits@3":"0.664"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.03496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03496"}},"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/raphaelsty/mkb","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dfdazac/blp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"1ab7d265b717db60","entry":"complex_score","repo":"dfdazac/blp","repo_kind":"official","path":"models.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ab7d265b717db60"}},{"code_sha256_prefix":"4de8ec87799ab1b4","entry":"distmult_score","repo":"dfdazac/blp","repo_kind":"official","path":"models.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4de8ec87799ab1b4"}},{"code_sha256_prefix":"4205ada232da5c54","entry":"file_to_ids","repo":"dfdazac/blp","repo_kind":"official","path":"data.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4205ada232da5c54"}},{"code_sha256_prefix":"a3936f53f9d93ed1","entry":"get_negative_sampling_indices","repo":"dfdazac/blp","repo_kind":"official","path":"data.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3936f53f9d93ed1"}},{"code_sha256_prefix":"8f2e45be8b37061d","entry":"get_triple_filters","repo":"dfdazac/blp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f2e45be8b37061d"}},{"code_sha256_prefix":"aa62acaf56a8519a","entry":"make_ent2idx","repo":"dfdazac/blp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa62acaf56a8519a"}},{"code_sha256_prefix":"3f0f68e2573aecf3","entry":"transe_score","repo":"dfdazac/blp","repo_kind":"official","path":"models.py","file_url":"https://github.com/dfdazac/blp/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f0f68e2573aecf3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}