{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1606.07298","atlas_url":"https://app.syntology.ai/?focus=1606.07298","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1606.07298"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1606.07298\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1606.07298"},"call":"get_concepts_for_paper(arxiv_id=\"1606.07298\")"}],"by_repo":[{"repo":"plkumjorn/FIND","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"07fc54052c0ff6554f1246d94a4f9c9ffcd7c1859fc8ebd0f9535d4c6d03d944","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}