{"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/rationale-augmented-convolutional-neural","title":"Rationale-Augmented Convolutional Neural Networks for Text Classification","arxiv_id":"1605.04469","date":"2016-05-14","proceeding":"EMNLP 2016 11","authors":["Ye Zhang","Iain Marshall","Byron C. Wallace"],"abstract":"We present a new Convolutional Neural Network (CNN) model for text\nclassification that jointly exploits labels on documents and their component\nsentences. Specifically, we consider scenarios in which annotators explicitly\nmark sentences (or snippets) that support their overall document\ncategorization, i.e., they provide rationales. Our model exploits such\nsupervision via a hierarchical approach in which each document is represented\nby a linear combination of the vector representations of its component\nsentences. We propose a sentence-level convolutional model that estimates the\nprobability that a given sentence is a rationale, and we then scale the\ncontribution of each sentence to the aggregate document representation in\nproportion to these estimates. Experiments on five classification datasets that\nhave document labels and associated rationales demonstrate that our approach\nconsistently outperforms strong baselines. Moreover, our model naturally\nprovides explanations for its predictions.","url_abs":"http://arxiv.org/abs/1605.04469v3","url_pdf":"http://arxiv.org/pdf/1605.04469v3.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":"rationale-augmented-convolutional-neural","repo_url":"https://github.com/bwallace/rationale-CNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"rationale-augmented-convolutional-neural","repo_url":"https://github.com/yezhang-xiaofan/Rationale-CNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.04469","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}