{"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/indosum-a-new-benchmark-dataset-for","title":"IndoSum: A New Benchmark Dataset for Indonesian Text Summarization","arxiv_id":"1810.05334","date":"2018-10-12","proceeding":null,"authors":["Kemal Kurniawan","Samuel Louvan"],"abstract":"Automatic text summarization is generally considered as a challenging task in\nthe NLP community. One of the challenges is the publicly available and large\ndataset that is relatively rare and difficult to construct. The problem is even\nworse for low-resource languages such as Indonesian. In this paper, we present\nIndoSum, a new benchmark dataset for Indonesian text summarization. The dataset\nconsists of news articles and manually constructed summaries. Notably, the\ndataset is almost 200x larger than the previous Indonesian summarization\ndataset of the same domain. We evaluated various extractive summarization\napproaches and obtained encouraging results which demonstrate the usefulness of\nthe dataset and provide baselines for future research. The code and the dataset\nare available online under permissive licenses.","url_abs":"http://arxiv.org/abs/1810.05334v5","url_pdf":"http://arxiv.org/pdf/1810.05334v5.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":"indosum-a-new-benchmark-dataset-for","repo_url":"https://github.com/kata-ai/indosum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"indosum","name":"IndoSum","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1810.05334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.05334"}},"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/kata-ai/indosum","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"4eb4c8c3886e74ea","entry":"conv2d","repo":"kata-ai/indosum","repo_kind":"official","path":"neuralsum/model.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/neuralsum/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4eb4c8c3886e74ea"}},{"code_sha256_prefix":"5eb10ec12599e2be","entry":"create_outlier_detector","repo":"kata-ai/indosum","repo_kind":"official","path":"prep_outliers.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/prep_outliers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5eb10ec12599e2be"}},{"code_sha256_prefix":"0974dc730415a7d5","entry":"get_filename","repo":"kata-ai/indosum","repo_kind":"official","path":"create_splits.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/create_splits.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0974dc730415a7d5"}},{"code_sha256_prefix":"a430b52d59f4c220","entry":"highway","repo":"kata-ai/indosum","repo_kind":"official","path":"neuralsum/model.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/neuralsum/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a430b52d59f4c220"}},{"code_sha256_prefix":"56acd0083cfb2521","entry":"linear","repo":"kata-ai/indosum","repo_kind":"official","path":"neuralsum/model.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/neuralsum/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56acd0083cfb2521"}},{"code_sha256_prefix":"cf5f87ab64fc2a27","entry":"read_jsonl","repo":"kata-ai/indosum","repo_kind":"official","path":"prep_outliers.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/prep_outliers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf5f87ab64fc2a27"}},{"code_sha256_prefix":"4f974cee3d9a25e5","entry":"train_for_paras_length","repo":"kata-ai/indosum","repo_kind":"official","path":"prep_outliers.py","file_url":"https://github.com/kata-ai/indosum/blob/HEAD/prep_outliers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f974cee3d9a25e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}