{"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/interpretable-and-compositional-relation","title":"Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder","arxiv_id":"1805.09547","date":"2018-05-24","proceeding":"ACL 2018 7","authors":["Ryo Takahashi","Ran Tian","Kentaro Inui"],"abstract":"Embedding models for entities and relations are extremely useful for\nrecovering missing facts in a knowledge base. Intuitively, a relation can be\nmodeled by a matrix mapping entity vectors. However, relations reside on low\ndimension sub-manifolds in the parameter space of arbitrary matrices---for one\nreason, composition of two relations $\\boldsymbol{M}_1,\\boldsymbol{M}_2$ may\nmatch a third $\\boldsymbol{M}_3$ (e.g. composition of relations\ncurrency_of_country and country_of_film usually matches\ncurrency_of_film_budget), which imposes compositional constraints to be\nsatisfied by the parameters (i.e. $\\boldsymbol{M}_1\\cdot\n\\boldsymbol{M}_2\\approx \\boldsymbol{M}_3$). In this paper we investigate a\ndimension reduction technique by training relations jointly with an\nautoencoder, which is expected to better capture compositional constraints. We\nachieve state-of-the-art on Knowledge Base Completion tasks with strongly\nimproved Mean Rank, and show that joint training with an autoencoder leads to\ninterpretable sparse codings of relations, helps discovering compositional\nconstraints and benefits from compositional training. Our source code is\nreleased at github.com/tianran/glimvec.","url_abs":"http://arxiv.org/abs/1805.09547v1","url_pdf":"http://arxiv.org/pdf/1805.09547v1.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":"interpretable-and-compositional-relation","repo_url":"https://github.com/tianran/glimvec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}