{"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/concurrent-learning-of-semantic-relations","title":"Concurrent Learning of Semantic Relations","arxiv_id":"1807.10076","date":"2018-07-26","proceeding":null,"authors":["Georgios Balikas","Gaël Dias","Rumen Moraliyski","Massih-Reza Amini"],"abstract":"Discovering whether words are semantically related and identifying the\nspecific semantic relation that holds between them is of crucial importance for\nNLP as it is essential for tasks like query expansion in IR. Within this\ncontext, different methodologies have been proposed that either exclusively\nfocus on a single lexical relation (e.g. hypernymy vs. random) or learn\nspecific classifiers capable of identifying multiple semantic relations (e.g.\nhypernymy vs. synonymy vs. random). In this paper, we propose another way to\nlook at the problem that relies on the multi-task learning paradigm. In\nparticular, we want to study whether the learning process of a given semantic\nrelation (e.g. hypernymy) can be improved by the concurrent learning of another\nsemantic relation (e.g. co-hyponymy). Within this context, we particularly\nexamine the benefits of semi-supervised learning where the training of a\nprediction function is performed over few labeled data jointly with many\nunlabeled ones. Preliminary results based on simple learning strategies and\nstate-of-the-art distributional feature representations show that concurrent\nlearning can lead to improvements in a vast majority of tested situations.","url_abs":"http://arxiv.org/abs/1807.10076v3","url_pdf":"http://arxiv.org/pdf/1807.10076v3.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":"concurrent-learning-of-semantic-relations","repo_url":"https://github.com/Houssam93/MultiTask-Learning-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"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}