{"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/improving-factual-completeness-and","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","arxiv_id":"2010.10042","date":"2020-10-20","proceeding":"NAACL 2021 4","authors":["Yasuhide Miura","Yuhao Zhang","Emily Bao Tsai","Curtis P. Langlotz","Dan Jurafsky"],"abstract":"Neural image-to-text radiology report generation systems offer the potential to improve radiology reporting by reducing the repetitive process of report drafting and identifying possible medical errors. However, existing report generation systems, despite achieving high performances on natural language generation metrics such as CIDEr or BLEU, still suffer from incomplete and inconsistent generations. Here we introduce two new simple rewards to encourage the generation of factually complete and consistent radiology reports: one that encourages the system to generate radiology domain entities consistent with the reference, and one that uses natural language inference to encourage these entities to be described in inferentially consistent ways. We combine these with the novel use of an existing semantic equivalence metric (BERTScore). We further propose a report generation system that optimizes these rewards via reinforcement learning. On two open radiology report datasets, our system substantially improved the F1 score of a clinical information extraction performance by +22.1 (Delta +63.9%). We further show via a human evaluation and a qualitative analysis that our system leads to generations that are more factually complete and consistent compared to the baselines.","url_abs":"https://arxiv.org/abs/2010.10042v2","url_pdf":"https://arxiv.org/pdf/2010.10042v2.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":"improving-factual-completeness-and","repo_url":"https://github.com/ysmiura/ifcc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improving-factual-completeness-and","repo_url":"https://github.com/jbdel/vilmedic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improving-factual-completeness-and","repo_url":"https://github.com/mudabek/encoding-cxr-report-gen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.10042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10042"}},"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/ysmiura/ifcc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jbdel/vilmedic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mudabek/encoding-cxr-report-gen","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"1d5cd4a2a1c96249","entry":"make_batch","repo":"ysmiura/ifcc","repo_kind":"official","path":"eval_prf.py","file_url":"https://github.com/ysmiura/ifcc/blob/HEAD/eval_prf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d5cd4a2a1c96249"}},{"code_sha256_prefix":"b806dbc858d7c36f","entry":"rename_state_dict_keys","repo":"mudabek/encoding-cxr-report-gen","repo_kind":"listed","path":"custom_models.py","file_url":"https://github.com/mudabek/encoding-cxr-report-gen/blob/HEAD/custom_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b806dbc858d7c36f"}},{"code_sha256_prefix":"0b1d99654ca7d814","entry":"tokenize","repo":"ysmiura/ifcc","repo_kind":"official","path":"eval_prf.py","file_url":"https://github.com/ysmiura/ifcc/blob/HEAD/eval_prf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b1d99654ca7d814"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}