{"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 (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":27,"of":27,"tagged_in_all":145,"items":[{"url":"/paper/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","title":"Applying the Transformer to Character-level Transduction","date":"2020-05-20","arxiv_id":"2005.10213","repositories_listed":3,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":2}},{"url":"/paper/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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","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","title":"Evaluating Informal-Domain Word Representations With UrbanDictionary","date":"2016-06-27","arxiv_id":"1606.08270","repositories_listed":1,"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"},"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"}}