{"url":"/task/punctuation-restoration","name":"Punctuation Restoration","slug":"punctuation-restoration","description_markdown":"Punctuation Restoration","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":51,"papers_with_code":19,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/lepiszcze","name":"LEPISZCZE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/turkish-punctuation-restoration","name":"Turkish Punctuation Restoration","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":19,"of":19,"tagged_in_all":51,"items":[{"url":"/paper/bartpho-pre-trained-sequence-to-sequence","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","date":"2021-09-20","arxiv_id":"2109.09701","repositories_listed":3,"syntology":null},{"url":"/paper/heritage-an-end-to-end-web-platform-for","title":"HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja","date":"2025-01-21","arxiv_id":"2501.11951","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-classical-chinese-help-quantifying","title":"When Does Classical Chinese Help? Quantifying Cross-Lingual Transfer in Hanja and Kanbun","date":"2024-11-07","arxiv_id":"2411.04822","repositories_listed":1,"syntology":null},{"url":"/paper/spontaneous-informal-speech-dataset-for","title":"Spontaneous Informal Speech Dataset for Punctuation Restoration","date":"2024-09-17","arxiv_id":"2409.11241","repositories_listed":1,"syntology":null},{"url":"/paper/punctuation-restoration-improves-structure","title":"Punctuation Restoration Improves Structure Understanding Without Supervision","date":"2024-02-13","arxiv_id":"2402.08382","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-punctuation-restoration-for","title":"Transformer Based Punctuation Restoration for Turkish","date":"2023-09-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-small-and-fast-bert-for-chinese-medical","title":"A Small and Fast BERT for Chinese Medical Punctuation Restoration","date":"2023-08-24","arxiv_id":"2308.12568","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-ensemble-architecture-for","title":"Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network","date":"2023-02-26","arxiv_id":"2302.13376","repositories_listed":1,"syntology":null},{"url":"/paper/punctuation-restoration-for-singaporean","title":"Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin","date":"2022-12-10","arxiv_id":"2212.05356","repositories_listed":1,"syntology":null},{"url":"/paper/behancepr-a-punctuation-restoration-dataset","title":"BehancePR: A Punctuation Restoration Dataset for Livestreaming Video Transcript","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/indic-punct-an-automatic-punctuation","title":"indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languages","date":"2022-03-31","arxiv_id":"2203.16825","repositories_listed":1,"syntology":null},{"url":"/paper/vakyansh-asr-toolkit-for-low-resource-indic","title":"Vakyansh: ASR Toolkit for Low Resource Indic languages","date":"2022-03-30","arxiv_id":"2203.16512","repositories_listed":1,"syntology":null},{"url":"/paper/a-context-aware-feature-fusion-framework-for","title":"A Context-Aware Feature Fusion Framework for Punctuation Restoration","date":"2022-03-23","arxiv_id":"2203.12487","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-punctuation-restoration","title":"Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus","date":"2022-01-24","arxiv_id":"2202.00468","repositories_listed":1,"syntology":null},{"url":"/paper/token-level-supervised-contrastive-learning","title":"Token-Level Supervised Contrastive Learning for Punctuation Restoration","date":"2021-07-19","arxiv_id":"2107.09099","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-external-pos-tagger-for","title":"Incorporating External POS Tagger for Punctuation Restoration","date":"2021-06-12","arxiv_id":"2106.06731","repositories_listed":1,"syntology":null},{"url":"/paper/punktuator-a-multilingual-punctuation","title":"PunKtuator: A Multilingual Punctuation Restoration System for Spoken and Written Text","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automatic-punctuation-restoration-with-bert","title":"Automatic punctuation restoration with BERT models","date":"2021-01-18","arxiv_id":"2101.07343","repositories_listed":1,"syntology":null},{"url":"/paper/punctuation-restoration-using-transformer","title":"Punctuation Restoration using Transformer Models for High-and Low-Resource Languages","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}