{"type":"ScholarlyArticle","title":"Building Joint Spaces for Relation Extraction","authors":[{"name":"Chang Wang","slug":"chang-wang","given":"Chang","family":"Wang","affiliation":""},{"name":"Liangliang Cao","slug":"liangliang-cao","given":"Liangliang","family":"Cao","affiliation":""},{"name":"James Fan","slug":"james-fan","given":"James","family":"Fan","affiliation":""}],"abstract":"In this paper, we present a novel approach for relation extraction using only term pairs as the input without textual features. We aim to build a single joint space for each relation which is then used to produce relation specific term embeddings. The proposed method fits particularly well for domains in which similar arguments are often associated with similar relations. It can also handle the situation when the labeled data is limited. The proposed method is evaluated both theoretically with a proof for the closed-form solution and experimentally with promising results on both DBpedia and medical relations.","doi":null,"url":"https://ijcai.org/proceedings/2016/417","pdf":"https://ijcai.org/proceedings/2016/0417.pdf","markdown":"https://ijcai.org/proceedings/2016/417.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/417","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":417,"pages":{"first":2936,"last":2941},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}