{"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/commonsense-knowledge-enhanced-embeddings-for","title":"Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge","arxiv_id":"1611.04146","date":"2016-11-13","proceeding":null,"authors":["Quan Liu","Hui Jiang","Zhen-Hua Ling","Xiaodan Zhu","Si Wei","Yu Hu"],"abstract":"In this paper, we propose commonsense knowledge enhanced embeddings (KEE) for\nsolving the Pronoun Disambiguation Problems (PDP). The PDP task we investigate\nin this paper is a complex coreference resolution task which requires the\nutilization of commonsense knowledge. This task is a standard first round test\nset in the 2016 Winograd Schema Challenge. In this task, traditional linguistic\nfeatures that are useful for coreference resolution, e.g. context and gender\ninformation, are no longer effective anymore. Therefore, the KEE models are\nproposed to provide a general framework to make use of commonsense knowledge\nfor solving the PDP problems. Since the PDP task doesn't have training data,\nthe KEE models would be used during the unsupervised feature extraction\nprocess. To evaluate the effectiveness of the KEE models, we propose to\nincorporate various commonsense knowledge bases, including ConceptNet, WordNet,\nand CauseCom, into the KEE training process. We achieved the best performance\nby applying the proposed methods to the 2016 Winograd Schema Challenge. In\naddition, experiments conducted on the standard PDP task indicate that, the\nproposed KEE models could solve the PDP problems by achieving 66.7% accuracy,\nwhich is a new state-of-the-art performance.","url_abs":"http://arxiv.org/abs/1611.04146v2","url_pdf":"http://arxiv.org/pdf/1611.04146v2.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":[],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"KEE+NKAM winner of the WSC2016","rank_in_archive_order":63,"of":82,"metrics":{"Accuracy":"58.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.04146","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}