{"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/what-is-relevant-in-a-text-document-an","title":"\"What is Relevant in a Text Document?\": An Interpretable Machine Learning Approach","arxiv_id":"1612.07843","date":"2016-12-23","proceeding":null,"authors":["Leila Arras","Franziska Horn","Grégoire Montavon","Klaus-Robert Müller","Wojciech Samek"],"abstract":"Text documents can be described by a number of abstract concepts such as\nsemantic category, writing style, or sentiment. Machine learning (ML) models\nhave been trained to automatically map documents to these abstract concepts,\nallowing to annotate very large text collections, more than could be processed\nby a human in a lifetime. Besides predicting the text's category very\naccurately, it is also highly desirable to understand how and why the\ncategorization process takes place. In this paper, we demonstrate that such\nunderstanding can be achieved by tracing the classification decision back to\nindividual words using layer-wise relevance propagation (LRP), a recently\ndeveloped technique for explaining predictions of complex non-linear\nclassifiers. We train two word-based ML models, a convolutional neural network\n(CNN) and a bag-of-words SVM classifier, on a topic categorization task and\nadapt the LRP method to decompose the predictions of these models onto words.\nResulting scores indicate how much individual words contribute to the overall\nclassification decision. This enables one to distill relevant information from\ntext documents without an explicit semantic information extraction step. We\nfurther use the word-wise relevance scores for generating novel vector-based\ndocument representations which capture semantic information. Based on these\ndocument vectors, we introduce a measure of model explanatory power and show\nthat, although the SVM and CNN models perform similarly in terms of\nclassification accuracy, the latter exhibits a higher level of explainability\nwhich makes it more comprehensible for humans and potentially more useful for\nother applications.","url_abs":"http://arxiv.org/abs/1612.07843v1","url_pdf":"http://arxiv.org/pdf/1612.07843v1.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":"what-is-relevant-in-a-text-document-an","repo_url":"https://github.com/sebastian-lapuschkin/lrp_toolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.07843","atlas_url":"https://app.syntology.ai/?focus=1612.07843","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":"1612.07843"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.07843\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.07843"},"call":"get_concepts_for_paper(arxiv_id=\"1612.07843\")"}],"by_repo":[{"repo":"sebastian-lapuschkin/lrp_toolbox","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":"5447fff22b8cef486b9bb9579fb6afed7b02448135bee043b41e9984702a4e87","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}