{"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/evaluation-of-unsupervised-compositional","title":"Evaluation of Unsupervised Compositional Representations","arxiv_id":"1806.04713","date":"2018-06-12","proceeding":"COLING 2018 8","authors":["Hanan Aldarmaki","Mona Diab"],"abstract":"We evaluated various compositional models, from bag-of-words representations\nto compositional RNN-based models, on several extrinsic supervised and\nunsupervised evaluation benchmarks. Our results confirm that weighted vector\naveraging can outperform context-sensitive models in most benchmarks, but\nstructural features encoded in RNN models can also be useful in certain\nclassification tasks. We analyzed some of the evaluation datasets to identify\nthe aspects of meaning they measure and the characteristics of the various\nmodels that explain their performance variance.","url_abs":"http://arxiv.org/abs/1806.04713v2","url_pdf":"http://arxiv.org/pdf/1806.04713v2.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":"evaluation-of-unsupervised-compositional","repo_url":"https://github.com/h-aldarmaki/sentence_eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}