{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":51,"of":51,"of_with_code":19,"tagged_in_all":51,"counts":{"archive_papers_tagged":51,"with_a_code_link":19,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":51,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/bartpho-pre-trained-sequence-to-sequence","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"granary-speech-recognition-and-translation","title":"Granary: Speech Recognition and Translation Dataset in 25 European Languages","date":"2025-05-19","arxiv_id":"2505.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-correction-for-full-text-speech","title":"Chain of Correction for Full-text Speech Recognition with Large Language Models","date":"2025-04-02","arxiv_id":"2504.01519","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-2-tf-robust-all-neural-text","title":"Universal-2-TF: Robust All-Neural Text Formatting for ASR","date":"2025-01-10","arxiv_id":"2501.05948","repositories_listed":0,"syntology":null},{"url":null,"slug":"fotheidil-an-automatic-transcription-system","title":"Fotheidil: an Automatic Transcription System for the Irish Language","date":"2024-12-31","arxiv_id":"2501.00509","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-text-error-correction-for-chinese-speech","title":"Full-text Error Correction for Chinese Speech Recognition with Large Language Model","date":"2024-09-12","arxiv_id":"2409.07790","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-based-punctuation-restoration-with","title":"LLaMA based Punctuation Restoration With Forward Pass Only Decoding","date":"2024-08-09","arxiv_id":"2408.11845","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolving-transcription-ambiguity-in-spanish","title":"Resolving Transcription Ambiguity in Spanish: A Hybrid Acoustic-Lexical System for Punctuation Restoration","date":"2024-02-05","arxiv_id":"2402.03519","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-restoration-model-and-spacing","title":"Punctuation restoration Model and Spacing Model for Korean Ancient Document","date":"2023-12-19","arxiv_id":"2312.11881","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-punctuation-restoration-with-data","title":"Boosting Punctuation Restoration with Data Generation and Reinforcement Learning","date":"2023-07-24","arxiv_id":"2307.12949","repositories_listed":0,"syntology":null},{"url":null,"slug":"ff2-a-feature-fusion-two-stream-framework-for","title":"FF2: A Feature Fusion Two-Stream Framework for Punctuation Restoration","date":"2022-11-09","arxiv_id":"2211.04699","repositories_listed":0,"syntology":null},{"url":null,"slug":"vietnamese-capitalization-and-punctuation","title":"Vietnamese Capitalization and Punctuation Recovery Models","date":"2022-07-04","arxiv_id":"2207.01312","repositories_listed":0,"syntology":null},{"url":null,"slug":"bazinga-a-dataset-for-multi-party-dialogues","title":"Bazinga! A Dataset for Multi-Party Dialogues Structuring","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-restoration-in-spanish-customer","title":"Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning","date":"2022-05-27","arxiv_id":"2205.13961","repositories_listed":0,"syntology":null},{"url":"/paper/punctuation-restoration","slug":"punctuation-restoration","title":"SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions","date":"2022-02-19","arxiv_id":"2202.09695","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-restoration-in-swedish-through","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","date":"2022-02-14","arxiv_id":"2202.06769","repositories_listed":0,"syntology":null},{"url":null,"slug":"capitalization-and-punctuation-restoration-a","title":"Capitalization and Punctuation Restoration: a Survey","date":"2021-11-21","arxiv_id":"2111.10746","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-punctuation-restoration-for","title":"Comprehensive Punctuation Restoration for English and Polish","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"virapart-a-text-refinement-framework-for-asr","title":"ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian","date":"2021-10-18","arxiv_id":"2110.09086","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-punctuation-restoration-for-speech","title":"Improving Punctuation Restoration for Speech Transcripts via External Data","date":"2021-10-01","arxiv_id":"2110.00560","repositories_listed":0,"syntology":null},{"url":null,"slug":"qasr-qcri-aljazeera-speech-resource-a-large-1","title":"QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"qasr-qcri-aljazeera-speech-resource-a-large","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","date":"2021-06-24","arxiv_id":"2106.13000","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-joint-modeling-of-multiple-spoken","title":"Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens","date":"2021-06-23","arxiv_id":"2106.12131","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-summarization-of-call-transcripts","title":"Extractive Summarization of Call Transcripts","date":"2021-03-19","arxiv_id":"2103.10599","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-automatic-punctuation-restoration","title":"Efficient Automatic Punctuation Restoration Using Bidirectional Transformers with Robust Inference","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpus-for-japanese-spoken-to","title":"Parallel Corpus for Japanese Spoken-to-Written Style Conversion","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-prediction-in-spontaneous","title":"Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?","date":"2020-04-13","arxiv_id":"2004.05985","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-transfer-learning-for-punctuation","title":"Adversarial Transfer Learning for Punctuation Restoration","date":"2020-04-01","arxiv_id":"2004.00248","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-capitalization-and","title":"Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging","date":"2019-08-07","arxiv_id":"1908.02404","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-model-for-punctuation-in","title":"A Generative Model for Punctuation in Dependency Trees","date":"2019-06-26","arxiv_id":"1906.11298","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-you-correct-run-on-sentences-its-not","title":"How do you correct run-on sentences it's not as easy as it seems","date":"2018-09-21","arxiv_id":"1809.08298","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dictations-to-clinical-reports-using","title":"From dictations to clinical reports using machine translation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-punctuation-restoration-in","title":"Deep Learning for Punctuation Restoration in Medical Reports","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"848aaf1d3c2c415da3a50c1e6554d55167777e68c1e3da79f0f208f2463eba47","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}