{"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/text-normalization","name":"Text Normalization","slug":"text-normalization","description_markdown":null,"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":"derived"},"counts":{"papers_tagged":145,"papers_with_code":27,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":2,"rows_per_page":100,"shown":100,"of":145,"of_with_code":27,"tagged_in_all":145,"counts":{"archive_papers_tagged":145,"with_a_code_link":27,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":145,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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/shallow-fusion-of-weighted-finite-state","slug":"shallow-fusion-of-weighted-finite-state","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","date":"2022-03-29","arxiv_id":"2203.15917","repositories_listed":3,"syntology":null},{"url":"/paper/applying-the-transformer-to-character-level","slug":"applying-the-transformer-to-character-level","title":"Applying the Transformer to Character-level Transduction","date":"2020-05-20","arxiv_id":"2005.10213","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/applying-the-transformer-to-character-level#ran","syntology_url":"https://syntology.ai/paper/2005.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10213"}},"official":{"repos":["shijie-wu/neural-transducer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/hinglishnorm-a-corpus-of-hindi-english-code","slug":"hinglishnorm-a-corpus-of-hindi-english-code","title":"hinglishNorm -- A Corpus of Hindi-English Code Mixed Sentences for Text Normalization","date":"2020-10-18","arxiv_id":"2010.08974","repositories_listed":2,"syntology":null},{"url":"/paper/a-large-scale-comparison-of-historical-text","slug":"a-large-scale-comparison-of-historical-text","title":"A Large-Scale Comparison of Historical Text Normalization Systems","date":"2019-04-03","arxiv_id":"1904.02036","repositories_listed":2,"syntology":null},{"url":"/paper/encoder-decoder-methods-for-text","slug":"encoder-decoder-methods-for-text","title":"Encoder-Decoder Methods for Text Normalization","date":"2018-08-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/digestion-algorithm-in-hierarchical-symbolic","slug":"digestion-algorithm-in-hierarchical-symbolic","title":"Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment","date":"2024-12-18","arxiv_id":"2412.14054","repositories_listed":1,"syntology":null},{"url":"/paper/vnlp-turkish-nlp-package","slug":"vnlp-turkish-nlp-package","title":"VNLP: Turkish NLP Package","date":"2024-03-02","arxiv_id":"2403.01309","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-for-front-end-text","slug":"multi-task-learning-for-front-end-text","title":"Multi-Task Learning for Front-End Text Processing in TTS","date":"2024-01-12","arxiv_id":"2401.06321","repositories_listed":1,"syntology":null},{"url":"/paper/extending-whisper-with-prompt-tuning-to","slug":"extending-whisper-with-prompt-tuning-to","title":"Extending Whisper with prompt tuning to target-speaker ASR","date":"2023-12-13","arxiv_id":"2312.08079","repositories_listed":1,"syntology":null},{"url":"/paper/text-normalization-for-endangered-languages","slug":"text-normalization-for-endangered-languages","title":"Text normalization for low-resource languages: the case of Ligurian","date":"2022-06-16","arxiv_id":"2206.07861","repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-chinese-text-normalization","slug":"an-end-to-end-chinese-text-normalization","title":"An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer","date":"2022-03-31","arxiv_id":"2203.16954","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/scicap-generating-captions-for-scientific","slug":"scicap-generating-captions-for-scientific","title":"SciCap: Generating Captions for Scientific Figures","date":"2021-10-22","arxiv_id":"2110.11624","repositories_listed":1,"syntology":null},{"url":"/paper/hui-audio-corpus-german-a-high-quality-tts","slug":"hui-audio-corpus-german-a-high-quality-tts","title":"HUI-Audio-Corpus-German: A high quality TTS dataset","date":"2021-06-11","arxiv_id":"2106.06309","repositories_listed":1,"syntology":null},{"url":"/paper/proteno-text-normalization-with-limited-data","slug":"proteno-text-normalization-with-limited-data","title":"Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems","date":"2021-04-15","arxiv_id":"2104.07777","repositories_listed":1,"syntology":null},{"url":"/paper/nemo-inverse-text-normalization-from","slug":"nemo-inverse-text-normalization-from","title":"NeMo Inverse Text Normalization: From Development To Production","date":"2021-04-11","arxiv_id":"2104.05055","repositories_listed":1,"syntology":null},{"url":"/paper/an-unsupervised-normalization-algorithm-for","slug":"an-unsupervised-normalization-algorithm-for","title":"An Unsupervised Normalization Algorithm for Noisy Text: A Case Study for Information Retrieval and Stance Detection","date":"2021-01-09","arxiv_id":"2101.03303","repositories_listed":1,"syntology":null},{"url":"/paper/seq2edits-sequence-transduction-using-span","slug":"seq2edits-sequence-transduction-using-span","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","date":"2020-09-23","arxiv_id":"2009.11136","repositories_listed":1,"syntology":null},{"url":"/paper/inducing-language-agnostic-multilingual","slug":"inducing-language-agnostic-multilingual","title":"Inducing Language-Agnostic Multilingual Representations","date":"2020-08-20","arxiv_id":"2008.09112","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-evaluate-word-representations-of","slug":"how-to-evaluate-word-representations-of","title":"How to Evaluate Word Representations of Informal Domain?","date":"2019-11-12","arxiv_id":"1911.04669","repositories_listed":1,"syntology":null},{"url":"/paper/dialect-text-normalization-to-normative","slug":"dialect-text-normalization-to-normative","title":"Dialect Text Normalization to Normative Standard Finnish","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adapting-sequence-to-sequence-models-for-text","slug":"adapting-sequence-to-sequence-models-for-text","title":"Adapting Sequence to Sequence models for Text Normalization in Social Media","date":"2019-04-12","arxiv_id":"1904.06100","repositories_listed":1,"syntology":null},{"url":"/paper/a-character-level-approach-to-the-text","slug":"a-character-level-approach-to-the-text","title":"A Character-Level Approach to the Text Normalization Problem Based on a New Causal Encoder","date":"2019-03-06","arxiv_id":"1903.02642","repositories_listed":1,"syntology":null},{"url":"/paper/text-normalization-using-memory-augmented","slug":"text-normalization-using-memory-augmented","title":"Text normalization using memory augmented neural networks","date":"2018-05-31","arxiv_id":"1806.00044","repositories_listed":1,"syntology":null},{"url":"/paper/machine-translation-of-low-resource-spoken","slug":"machine-translation-of-low-resource-spoken","title":"Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German","date":"2017-10-30","arxiv_id":"1710.11035","repositories_listed":1,"syntology":null},{"url":"/paper/rnn-approaches-to-text-normalization-a","slug":"rnn-approaches-to-text-normalization-a","title":"RNN Approaches to Text Normalization: A Challenge","date":"2016-10-31","arxiv_id":"1611.00068","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-informal-domain-word","slug":"evaluating-informal-domain-word","title":"Evaluating Informal-Domain Word Representations With UrbanDictionary","date":"2016-06-27","arxiv_id":"1606.08270","repositories_listed":1,"syntology":null},{"url":null,"slug":"dynamic-context-aware-streaming-pretrained","title":"Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization","date":"2025-05-30","arxiv_id":"2505.24229","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-sentiment-insights-from-x-using","title":"Visualizing Public Opinion on X: A Real-Time Sentiment Dashboard Using VADER and DistilBERT","date":"2025-04-21","arxiv_id":"2504.15448","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":"misspellings-in-natural-language-processing-a","title":"Misspellings in Natural Language Processing: A survey","date":"2025-01-28","arxiv_id":"2501.16836","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":"neural-text-normalization-for-luxembourgish","title":"Neural Text Normalization for Luxembourgish using Real-Life Variation Data","date":"2024-12-12","arxiv_id":"2412.09383","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-driven-smishing-detection","title":"Machine Learning Driven Smishing Detection Framework for Mobile Security","date":"2024-12-09","arxiv_id":"2412.09641","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-deep-learning-for-legal-text-analysis","title":"Hybrid Deep Learning for Legal Text Analysis: Predicting Punishment Durations in Indonesian Court Rulings","date":"2024-10-26","arxiv_id":"2410.20104","repositories_listed":0,"syntology":null},{"url":null,"slug":"wer-we-stand-benchmarking-urdu-asr-models","title":"WER We Stand: Benchmarking Urdu ASR Models","date":"2024-09-17","arxiv_id":"2409.11252","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":"historical-german-text-normalization-using","title":"Historical German Text Normalization Using Type- and Token-Based Language Modeling","date":"2024-09-04","arxiv_id":"2409.02841","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-lost-in-normalization-exploring","title":"What is lost in Normalization? Exploring Pitfalls in Multilingual ASR Model Evaluations","date":"2024-09-04","arxiv_id":"2409.02449","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-text-normalization-relevant-for","title":"Is text normalization relevant for classifying medieval charters?","date":"2024-08-29","arxiv_id":"2408.16446","repositories_listed":0,"syntology":null},{"url":null,"slug":"positional-description-for-numerical","title":"Positional Description for Numerical Normalization","date":"2024-08-22","arxiv_id":"2408.12430","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-chime-8-dasr-challenge-for-generalizable","title":"The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization","date":"2024-07-23","arxiv_id":"2407.16447","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-dialect-identification-in","title":"Exploiting Dialect Identification in Automatic Dialectal Text Normalization","date":"2024-07-03","arxiv_id":"2407.03020","repositories_listed":0,"syntology":null},{"url":null,"slug":"prior-agnostic-multi-scale-contrastive-text","title":"Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling","date":"2024-04-14","arxiv_id":"2404.09192","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalization-of-lithuanian-text-using","title":"Normalization of Lithuanian Text Using Regular Expressions","date":"2023-12-29","arxiv_id":"2312.17660","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-chat-about-boring-problems-studying-gpt","title":"A Chat About Boring Problems: Studying GPT-based text normalization","date":"2023-09-23","arxiv_id":"2309.13426","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-robustness-of-neural-inverse-text","title":"Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Method","date":"2023-09-12","arxiv_id":"2309.08626","repositories_listed":0,"syntology":null},{"url":null,"slug":"ldeb-label-digitization-with-emotion","title":"LDEB -- Label Digitization with Emotion Binarization and Machine Learning for Emotion Recognition in Conversational Dialogues","date":"2023-06-03","arxiv_id":"2306.02193","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-front-end-framework-for-english","title":"A unified front-end framework for English text-to-speech synthesis","date":"2023-05-18","arxiv_id":"2305.10666","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-agnostic-data-driven-inverse-text","title":"Language Agnostic Data-Driven Inverse Text Normalization","date":"2023-01-20","arxiv_id":"2301.08506","repositories_listed":0,"syntology":null},{"url":"/paper/benchmarking-evaluation-metrics-for-code","slug":"benchmarking-evaluation-metrics-for-code","title":"Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition","date":"2022-11-22","arxiv_id":"2211.16319","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-fast-and-accurate-on-device-inverse","title":"Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition","date":"2022-11-07","arxiv_id":"2211.03721","repositories_listed":0,"syntology":null},{"url":null,"slug":"trscore-a-novel-gpt-based-readability-scorer","title":"TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection","date":"2022-10-27","arxiv_id":"2210.15104","repositories_listed":0,"syntology":null},{"url":null,"slug":"four-in-one-a-joint-approach-to-inverse-text","title":"Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition","date":"2022-10-26","arxiv_id":"2210.15063","repositories_listed":0,"syntology":null},{"url":null,"slug":"singlish-message-paraphrasing-a-joint-task-of","title":"Singlish Message Paraphrasing: A Joint Task of Creole Translation and Text Normalization","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"non-standard-vietnamese-word-detection-and","title":"Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech","date":"2022-09-07","arxiv_id":"2209.02971","repositories_listed":0,"syntology":null},{"url":null,"slug":"thutmose-tagger-single-pass-neural-model-for","title":"Thutmose Tagger: Single-pass neural model for Inverse Text Normalization","date":"2022-07-29","arxiv_id":"2208.00064","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-data-driven-inverse-text","title":"Improving Data Driven Inverse Text Normalization using Data Augmentation","date":"2022-07-20","arxiv_id":"2207.09674","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-text-normalization","title":"Adversarial Text Normalization","date":"2022-06-08","arxiv_id":"2206.04137","repositories_listed":0,"syntology":null},{"url":null,"slug":"boring-problems-are-sometimes-the-most","title":"Boring Problems Are Sometimes the Most Interesting","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jhu-iwslt-2022-dialect-speech-translation","title":"JHU IWSLT 2022 Dialect Speech Translation System Description","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seq-2-seq-based-refinement-of-asr-output-for","title":"Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture","date":"2022-03-29","arxiv_id":"2203.15833","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-models-of-text","title":"Transformer-based Models of Text Normalization for Speech Applications","date":"2022-02-01","arxiv_id":"2202.00153","repositories_listed":0,"syntology":null},{"url":null,"slug":"slam-a-unified-encoder-for-speech-and","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","date":"2021-10-20","arxiv_id":"2110.10329","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-randomized-algorithm-for-massive-text","title":"A Fast Randomized Algorithm for Massive Text Normalization","date":"2021-10-06","arxiv_id":"2110.03024","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-text-normalization-on-multiword","title":"The Impact of Text Normalization on Multiword Expressions Discovery in Persian","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-transformer-based-framework-for","title":"A Unified Transformer-based Framework for Duplex Text Normalization","date":"2021-08-23","arxiv_id":"2108.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"bdkg-at-mediqa-2021-system-report-for-the","title":"BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-data-in-icelandic-for-text","title":"Creating Data in Icelandic for Text Normalization","date":"2021-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-full-size-russian-complexly","title":"An analysis of full-size Russian complexly NER labelled corpus of Internet user reviews on the drugs based on deep learning and language neural nets","date":"2021-04-30","arxiv_id":"2105.00059","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-normalization-for-low-resource-languages","title":"Text Normalization for Low-Resource Languages of Africa","date":"2021-03-29","arxiv_id":"2103.15845","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapgn-masked-pointer-generator-network-for","title":"MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training","date":"2021-02-15","arxiv_id":"2102.07380","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-inverse-text-normalization","title":"Neural Inverse Text Normalization","date":"2021-02-12","arxiv_id":"2102.06380","repositories_listed":0,"syntology":null},{"url":null,"slug":"hinglishnorm-a-corpus-of-hindi-english-code-1","title":"hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-text-normalization-leveraging","title":"Neural text normalization leveraging similarities of strings and sounds","date":"2020-11-04","arxiv_id":"2011.02173","repositories_listed":0,"syntology":null},{"url":null,"slug":"service-oriented-text-to-sql-parsing","title":"Service-oriented Text-to-SQL Parsing","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tnt-text-normalization-based-pre-training-of","title":"TNT: Text Normalization based Pre-training of Transformers for Content Moderation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aggressive-language-detection-with-joint-text","title":"Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning","date":"2020-09-19","arxiv_id":"2009.09174","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-bayesian-trie-based-model-for-sms","title":"An improved Bayesian TRIE based model for SMS text normalization","date":"2020-08-04","arxiv_id":"2008.01297","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-multi-task-text-normalization-and","title":"Neural Multi-task Text Normalization and Sanitization with Pointer-Generator","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-contextual-historical-text","title":"Semi-supervised Contextual Historical Text Normalization","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"normalizing-text-using-language-modelling","title":"Normalizing Text using Language Modelling based on Phonetics and String Similarity","date":"2020-06-25","arxiv_id":"2006.14116","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-quality-and-stability-of-a","title":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer","date":"2020-06-02","arxiv_id":"2006.01416","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-spelling-correction-corpus-for-multiple","title":"A Spelling Correction Corpus for Multiple Arabic Dialects","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"burmese-speech-corpus-finite-state-text","title":"Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-parametric-text-normalization","title":"Data-Driven Parametric Text Normalization: Rapidly Scaling Finite-State Transduction Verbalizers to New Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-resources-for-automated-speech","title":"Developing Resources for Automated Speech Processing of Quebec French","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-multilingual-frontend-for-tts","title":"Scalable Multilingual Frontend for TTS","date":"2020-04-10","arxiv_id":"2004.04934","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-text-normalization-system-using","title":"A hybrid text normalization system using multi-head self-attention for mandarin","date":"2019-11-11","arxiv_id":"1911.04128","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-t-for-latency-controlled-asr-with","title":"RNN-T For Latency Controlled ASR With Improved Beam Search","date":"2019-11-05","arxiv_id":"1911.01629","repositories_listed":0,"syntology":null},{"url":null,"slug":"benefits-of-data-augmentation-for-nmt-based","title":"Benefits of Data Augmentation for NMT-based Text Normalization of User-Generated Content","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-neologism-normalization-using","title":"Unsupervised Neologism Normalization Using Embedding Space Mapping","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amharic-text-normalization-with-sequence-to","title":"Amharic Text Normalization with Sequence-to-Sequence Models","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-mt-approaches-for-text","title":"Comparing MT Approaches for Text Normalization","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"give-it-a-shot-few-shot-learning-to-normalize","title":"Give It a Shot: Few-shot Learning to Normalize ADR Mentions in Social Media Posts","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"historical-text-normalization-with-delayed","title":"Historical Text Normalization with Delayed Rewards","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"normalizing-non-canonical-turkish-texts-using","title":"Normalizing Non-canonical Turkish Texts Using Machine Translation Approaches","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-models-of-text-normalization-for","title":"Neural Models of Text Normalization for Speech Applications","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-text-normalization-with-subword-units","title":"Neural Text Normalization with Subword Units","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilevel-text-normalization-with-sequence","title":"Multilevel Text Normalization with Sequence-to-Sequence Networks and Multisource Learning","date":"2019-03-27","arxiv_id":"1903.11340","repositories_listed":0,"syntology":null}],"syntology_records":1,"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":1,"papers_where_code_ran_first_page":"/task/text-normalization/papers/ran/1","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":[{"order":"archive","page":2,"of":2,"url":"/task/text-normalization/papers/2","json":"/task/text-normalization/papers/2.json","rows":45},{"order":"ran","page":1,"of":1,"url":"/task/text-normalization/papers/ran/1","json":"/task/text-normalization/papers/ran/1.json","rows":1}],"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":"bd46b4f28b26ea00ecda78752e41eb23bc77acc4e753ab208469cbfc95daa969","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}