{"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/a-context-aware-citation-recommendation-model","title":"A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks","arxiv_id":"1903.06464","date":"2019-03-15","proceeding":null,"authors":["Chanwoo Jeong","Sion Jang","Hyuna Shin","Eunjeong Park","Sungchul Choi"],"abstract":"With the tremendous growth in the number of scientific papers being\npublished, searching for references while writing a scientific paper is a\ntime-consuming process. A technique that could add a reference citation at the\nappropriate place in a sentence will be beneficial. In this perspective,\ncontext-aware citation recommendation has been researched upon for around two\ndecades. Many researchers have utilized the text data called the context\nsentence, which surrounds the citation tag, and the metadata of the target\npaper to find the appropriate cited research. However, the lack of\nwell-organized benchmarking datasets and no model that can attain high\nperformance has made the research difficult.\n  In this paper, we propose a deep learning based model and well-organized\ndataset for context-aware paper citation recommendation. Our model comprises a\ndocument encoder and a context encoder, which uses Graph Convolutional Networks\n(GCN) layer and Bidirectional Encoder Representations from Transformers (BERT),\nwhich is a pre-trained model of textual data. By modifying the related PeerRead\ndataset, we propose a new dataset called FullTextPeerRead containing context\nsentences to cited references and paper metadata. To the best of our knowledge,\nThis dataset is the first well-organized dataset for context-aware paper\nrecommendation. The results indicate that the proposed model with the proposed\ndatasets can attain state-of-the-art performance and achieve a more than 28%\nimprovement in mean average precision (MAP) and recall@k.","url_abs":"http://arxiv.org/abs/1903.06464v1","url_pdf":"http://arxiv.org/pdf/1903.06464v1.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":"a-context-aware-citation-recommendation-model","repo_url":"https://github.com/TeamLab/bert-gcn-for-paper-citation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"citation-recommendation","task_name":"Citation Recommendation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.06464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}