{"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/jointly-embedding-entities-and-text-with","title":"Jointly Embedding Entities and Text with Distant Supervision","arxiv_id":"1807.03399","date":"2018-07-09","proceeding":"WS 2018 7","authors":["Denis Newman-Griffis","Albert M. Lai","Eric Fosler-Lussier"],"abstract":"Learning representations for knowledge base entities and concepts is becoming\nincreasingly important for NLP applications. However, recent entity embedding\nmethods have relied on structured resources that are expensive to create for\nnew domains and corpora. We present a distantly-supervised method for jointly\nlearning embeddings of entities and text from an unnanotated corpus, using only\na list of mappings between entities and surface forms. We learn embeddings from\nopen-domain and biomedical corpora, and compare against prior methods that rely\non human-annotated text or large knowledge graph structure. Our embeddings\ncapture entity similarity and relatedness better than prior work, both in\nexisting biomedical datasets and a new Wikipedia-based dataset that we release\nto the community. Results on analogy completion and entity sense disambiguation\nindicate that entities and words capture complementary information that can be\neffectively combined for downstream use.","url_abs":"http://arxiv.org/abs/1807.03399v1","url_pdf":"http://arxiv.org/pdf/1807.03399v1.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":"jointly-embedding-entities-and-text-with","repo_url":"https://github.com/OSU-slatelab/JET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"jointly-embedding-entities-and-text-with","repo_url":"https://github.com/OSU-slatelab/WikiSRS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"wikisrs","name":"WikiSRS","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.03399","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}