{"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/predicting-conceptnet-path-quality-using","title":"Predicting ConceptNet Path Quality Using Crowdsourced Assessments of Naturalness","arxiv_id":"1902.07831","date":"2019-02-21","proceeding":null,"authors":["Yilun Zhou","Steven Schockaert","Julie A. Shah"],"abstract":"In many applications, it is important to characterize the way in which two\nconcepts are semantically related. Knowledge graphs such as ConceptNet provide\na rich source of information for such characterizations by encoding relations\nbetween concepts as edges in a graph. When two concepts are not directly\nconnected by an edge, their relationship can still be described in terms of the\npaths that connect them. Unfortunately, many of these paths are uninformative\nand noisy, which means that the success of applications that use such path\nfeatures crucially relies on their ability to select high-quality paths. In\nexisting applications, this path selection process is based on relatively\nsimple heuristics. In this paper we instead propose to learn to predict path\nquality from crowdsourced human assessments. Since we are interested in a\ngeneric task-independent notion of quality, we simply ask human participants to\nrank paths according to their subjective assessment of the paths' naturalness,\nwithout attempting to define naturalness or steering the participants towards\nparticular indicators of quality. We show that a neural network model trained\non these assessments is able to predict human judgments on unseen paths with\nnear optimal performance. Most notably, we find that the resulting path\nselection method is substantially better than the current heuristic approaches\nat identifying meaningful paths.","url_abs":"http://arxiv.org/abs/1902.07831v1","url_pdf":"http://arxiv.org/pdf/1902.07831v1.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":"predicting-conceptnet-path-quality-using","repo_url":"https://github.com/YilunZhou/path-naturalness-prediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07831","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}