{"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/polytuplet-loss-a-reverse-approach-to","title":"Deep Manifold Learning for Reading Comprehension and Logical Reasoning Tasks with Polytuplet Loss","arxiv_id":"2304.01046","date":"2023-04-03","proceeding":null,"authors":["Jeffrey Lu","Ivan Rodriguez"],"abstract":"The current trend in developing machine learning models for reading comprehension and logical reasoning tasks is focused on improving the models' abilities to understand and utilize logical rules. This work focuses on providing a novel loss function and accompanying model architecture that has more interpretable components than some other models by representing a common strategy employed by humans when given reading comprehension and logical reasoning tasks. Our strategy involves emphasizing relative accuracy over absolute accuracy and can theoretically produce the correct answer with incomplete knowledge. We examine the effectiveness of this strategy to solve reading comprehension and logical reasoning questions. The models were evaluated on the ReClor dataset, a challenging reading comprehension and logical reasoning benchmark. We propose the polytuplet loss function, which forces prioritization of learning the relative correctness of answer choices over learning the true accuracy of each choice. Our results indicate that models employing polytuplet loss outperform existing baseline models, though further research is required to quantify the benefits it may present.","url_abs":"https://arxiv.org/abs/2304.01046v4","url_pdf":"https://arxiv.org/pdf/2304.01046v4.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":"polytuplet-loss-a-reverse-approach-to","repo_url":"https://github.com/ussiamaboat/polytuplet-loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"polytuplet-loss-a-reverse-approach-to","repo_url":"https://github.com/ussiamaboat/research-paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}