{"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/evolutionary-data-measures-understanding-the","title":"Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks","arxiv_id":"1811.01910","date":"2018-11-05","proceeding":"CONLL 2018 10","authors":["Edward Collins","Nikolai Rozanov","Bingbing Zhang"],"abstract":"Classification tasks are usually analysed and improved through new model\narchitectures or hyperparameter optimisation but the underlying properties of\ndatasets are discovered on an ad-hoc basis as errors occur. However,\nunderstanding the properties of the data is crucial in perfecting models. In\nthis paper we analyse exactly which characteristics of a dataset best determine\nhow difficult that dataset is for the task of text classification. We then\npropose an intuitive measure of difficulty for text classification datasets\nwhich is simple and fast to calculate. We show that this measure generalises to\nunseen data by comparing it to state-of-the-art datasets and results. This\nmeasure can be used to analyse the precise source of errors in a dataset and\nallows fast estimation of how difficult a dataset is to learn. We searched for\nthis measure by training 12 classical and neural network based models on 78\nreal-world datasets, then use a genetic algorithm to discover the best measure\nof difficulty. Our difficulty-calculating code ( https://github.com/Wluper/edm\n) and datasets ( http://data.wluper.com ) are publicly available.","url_abs":"http://arxiv.org/abs/1811.01910v2","url_pdf":"http://arxiv.org/pdf/1811.01910v2.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":"evolutionary-data-measures-understanding-the","repo_url":"https://github.com/Wluper/edm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"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=1811.01910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01910"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Wluper/edm","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"cb4ec4382a076472","entry":"get_class_diversity","repo":"Wluper/edm","repo_kind":"official","path":"edm/metrics/difficulty_measures.py","file_url":"https://github.com/Wluper/edm/blob/HEAD/edm/metrics/difficulty_measures.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cb4ec4382a076472"}},{"code_sha256_prefix":"05d40eedd85372d6","entry":"get_minimum_hellinger_distance","repo":"Wluper/edm","repo_kind":"official","path":"edm/metrics/difficulty_measures.py","file_url":"https://github.com/Wluper/edm/blob/HEAD/edm/metrics/difficulty_measures.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"05d40eedd85372d6"}},{"code_sha256_prefix":"07ad2c79339cd6a4","entry":"get_mutual_information_from_count_dict","repo":"Wluper/edm","repo_kind":"official","path":"edm/metrics/difficulty_measures.py","file_url":"https://github.com/Wluper/edm/blob/HEAD/edm/metrics/difficulty_measures.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"07ad2c79339cd6a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}