{"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/explaining-predictions-of-non-linear","title":"Explaining Predictions of Non-Linear Classifiers in NLP","arxiv_id":"1606.07298","date":"2016-06-23","proceeding":"WS 2016 8","authors":["Leila Arras","Franziska Horn","Grégoire Montavon","Klaus-Robert Müller","Wojciech Samek"],"abstract":"Layer-wise relevance propagation (LRP) is a recently proposed technique for\nexplaining predictions of complex non-linear classifiers in terms of input\nvariables. In this paper, we apply LRP for the first time to natural language\nprocessing (NLP). More precisely, we use it to explain the predictions of a\nconvolutional neural network (CNN) trained on a topic categorization task. Our\nanalysis highlights which words are relevant for a specific prediction of the\nCNN. We compare our technique to standard sensitivity analysis, both\nqualitatively and quantitatively, using a \"word deleting\" perturbation\nexperiment, a PCA analysis, and various visualizations. All experiments\nvalidate the suitability of LRP for explaining the CNN predictions, which is\nalso in line with results reported in recent image classification studies.","url_abs":"http://arxiv.org/abs/1606.07298v1","url_pdf":"http://arxiv.org/pdf/1606.07298v1.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":"explaining-predictions-of-non-linear","repo_url":"https://github.com/plkumjorn/FIND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.07298","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}