{"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/model-comparison-for-semantic-grouping","title":"Model Comparison for Semantic Grouping","arxiv_id":"1904.13323","date":"2019-04-30","proceeding":null,"authors":["Francisco Vargas","Kamen Brestnichki","Nils Hammerla"],"abstract":"We introduce a probabilistic framework for quantifying the semantic\nsimilarity between two groups of embeddings. We formulate the task of semantic\nsimilarity as a model comparison task in which we contrast a generative model\nwhich jointly models two sentences versus one that does not. We illustrate how\nthis framework can be used for the Semantic Textual Similarity tasks using\nclear assumptions about how the embeddings of words are generated. We apply\nmodel comparison that utilises information criteria to address some of the\nshortcomings of Bayesian model comparison, whilst still penalising model\ncomplexity. We achieve competitive results by applying the proposed framework\nwith an appropriate choice of likelihood on the STS datasets.","url_abs":"http://arxiv.org/abs/1904.13323v2","url_pdf":"http://arxiv.org/pdf/1904.13323v2.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":"model-comparison-for-semantic-grouping","repo_url":"https://github.com/Babylonpartners/MCSG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sts","task_name":"STS"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}