{"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/chart-to-text-a-large-scale-benchmark-for","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","arxiv_id":"2203.06486","date":"2022-03-12","proceeding":"ACL 2022 5","authors":["Shankar Kantharaj","Rixie Tiffany Ko Leong","Xiang Lin","Ahmed Masry","Megh Thakkar","Enamul Hoque","Shafiq Joty"],"abstract":"Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and perceptual efforts. We present Chart-to-text, a large-scale benchmark with two datasets and a total of 44,096 charts covering a wide range of topics and chart types. We explain the dataset construction process and analyze the datasets. We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation techniques to tackle two problem variations: one assumes the underlying data table of the chart is available while the other needs to extract data from chart images. Our analysis with automatic and human evaluation shows that while our best models usually generate fluent summaries and yield reasonable BLEU scores, they also suffer from hallucinations and factual errors as well as difficulties in correctly explaining complex patterns and trends in charts.","url_abs":"https://arxiv.org/abs/2203.06486v3","url_pdf":"https://arxiv.org/pdf/2203.06486v3.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":"chart-to-text-a-large-scale-benchmark-for","repo_url":"https://github.com/vis-nlp/chart-to-text","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"chart-to-text-a-large-scale-benchmark-for","repo_url":"https://github.com/JasonObeid/Chart2Text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[{"slug":"chart-to-text","name":"Chart-to-text","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.06486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06486"}},"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/JasonObeid/Chart2Text","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vis-nlp/chart-to-text","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/visnlp/Chart-to-text","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":4,"ran_fixture":1},"by_repo_kind":{"named_in_paper":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":2,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"a6e1fd9026eb9bd4","entry":"addUnderscores","repo":"JasonObeid/Chart2Text","repo_kind":"listed","path":"utils/refactorTitles.py","file_url":"https://github.com/JasonObeid/Chart2Text/blob/HEAD/utils/refactorTitles.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6e1fd9026eb9bd4"}},{"code_sha256_prefix":"d009ee375d27bac5","entry":"getChartType","repo":"vis-nlp/chart-to-text","repo_kind":"named_in_paper","path":"baseline_models/Chart2Text/etc/BaselineSummarizer.py","file_url":"https://github.com/vis-nlp/chart-to-text/blob/HEAD/baseline_models/Chart2Text/etc/BaselineSummarizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d009ee375d27bac5"}},{"code_sha256_prefix":"8f27d8a61761cc13","entry":"groupSequence","repo":"JasonObeid/Chart2Text","repo_kind":"listed","path":"utils/refactorTitles.py","file_url":"https://github.com/JasonObeid/Chart2Text/blob/HEAD/utils/refactorTitles.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f27d8a61761cc13"}},{"code_sha256_prefix":"ab93e17de8534f24","entry":"openCaption","repo":"vis-nlp/chart-to-text","repo_kind":"named_in_paper","path":"baseline_models/Chart2Text/etc/BaselineSummarizer.py","file_url":"https://github.com/vis-nlp/chart-to-text/blob/HEAD/baseline_models/Chart2Text/etc/BaselineSummarizer.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ab93e17de8534f24"}},{"code_sha256_prefix":"4ecda318b485fa91","entry":"openData","repo":"vis-nlp/chart-to-text","repo_kind":"named_in_paper","path":"baseline_models/Chart2Text/etc/BaselineSummarizer.py","file_url":"https://github.com/vis-nlp/chart-to-text/blob/HEAD/baseline_models/Chart2Text/etc/BaselineSummarizer.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4ecda318b485fa91"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}