{"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/composing-distributed-representations-of","title":"Composing Distributed Representations of Relational Patterns","arxiv_id":"1707.07265","date":"2017-07-23","proceeding":"ACL 2016 8","authors":["Sho Takase","Naoaki Okazaki","Kentaro Inui"],"abstract":"Learning distributed representations for relation instances is a central\ntechnique in downstream NLP applications. In order to address semantic modeling\nof relational patterns, this paper constructs a new dataset that provides\nmultiple similarity ratings for every pair of relational patterns on the\nexisting dataset. In addition, we conduct a comparative study of different\nencoders including additive composition, RNN, LSTM, and GRU for composing\ndistributed representations of relational patterns. We also present Gated\nAdditive Composition, which is an enhancement of additive composition with the\ngating mechanism. Experiments show that the new dataset does not only enable\ndetailed analyses of the different encoders, but also provides a gauge to\npredict successes of distributed representations of relational patterns in the\nrelation classification task.","url_abs":"http://arxiv.org/abs/1707.07265v1","url_pdf":"http://arxiv.org/pdf/1707.07265v1.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":"composing-distributed-representations-of","repo_url":"https://github.com/takase/relPatSim","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"relational-pattern-similarity-dataset","name":"Relational Pattern Similarity Dataset","full_name":"Relational Pattern Similarity Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}