{"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/learning-sequence-encoders-for-temporal","title":"Learning Sequence Encoders for Temporal Knowledge Graph Completion","arxiv_id":"1809.03202","date":"2018-09-10","proceeding":"EMNLP 2018 10","authors":["Alberto García-Durán","Sebastijan Dumančić","Mathias Niepert"],"abstract":"Research on link prediction in knowledge graphs has mainly focused on static\nmulti-relational data. In this work we consider temporal knowledge graphs where\nrelations between entities may only hold for a time interval or a specific\npoint in time. In line with previous work on static knowledge graphs, we\npropose to address this problem by learning latent entity and relation type\nrepresentations. To incorporate temporal information, we utilize recurrent\nneural networks to learn time-aware representations of relation types which can\nbe used in conjunction with existing latent factorization methods. The proposed\napproach is shown to be robust to common challenges in real-world KGs: the\nsparsity and heterogeneity of temporal expressions. Experiments show the\nbenefits of our approach on four temporal KGs. The data sets are available\nunder a permissive BSD-3 license 1.","url_abs":"http://arxiv.org/abs/1809.03202v1","url_pdf":"http://arxiv.org/pdf/1809.03202v1.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":"learning-sequence-encoders-for-temporal","repo_url":"https://github.com/nle-ml/mmkb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"learning-sequence-encoders-for-temporal","repo_url":"https://github.com/bsantraigi/TA_TransE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-sequence-encoders-for-temporal","repo_url":"https://github.com/mniepert/mmkb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"temporal-knowledge-graph-completion","task_name":"Temporal Knowledge Graph Completion"}],"methods":[],"datasets_introduced":[{"slug":"icews","name":"ICEWS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03202","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}