Browse State-of-the-Art › Text Normalization

Text Normalization

27 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28

Natural Language Processing

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 145 · with a code link: 27 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 145 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 145, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 29 Mar 2022 3 repositories listed
    First, a non-deterministic WFST outputs all normalization candidates, and then a neural language model picks the best one -- similar to shallow fusion for automatic speech recognition.
  • The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks.
  • 18 Oct 2020 2 repositories listed
    We present hinglishNorm -- a human annotated corpus of Hindi-English code-mixed sentences for text normalization task.
  • 3 Apr 2019 2 repositories listed
    There is no consensus on the state-of-the-art approach to historical text normalization.
  • 1 Aug 2018 2 repositories listed
    Text normalization has been addressed with a variety of methods, most successfully with character-level statistical machine translation (CSMT).
  • 18 Dec 2024 1 repository listed
    Text Normalization and Semantic Parsing have numerous applications in natural language processing, such as natural language programming, paraphrasing, data augmentation, constructing expert systems, text matching, and…
  • 2 Mar 2024 1 repository listed
    In this work, we present VNLP: the first dedicated, complete, open-source, well-documented, lightweight, production-ready, state-of-the-art Natural Language Processing (NLP) package for the Turkish language.
  • 12 Jan 2024 1 repository listed
    We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph…
  • 13 Dec 2023 1 repository listed
    Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances.
  • 16 Jun 2022 1 repository listed
    Text normalization is a crucial technology for low-resource languages which lack rigid spelling conventions or that have undergone multiple spelling reforms.
  • 31 Mar 2022 1 repository listed
    Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural…
  • 31 Mar 2022 1 repository listed
    Automatic Speech Recognition (ASR) generates text which is most of the times devoid of any punctuation.
  • 22 Oct 2021 1 repository listed
    Researchers use figures to communicate rich, complex information in scientific papers.
  • 11 Jun 2021 1 repository listed
    The increasing availability of audio data on the internet lead to a multitude of datasets for development and training of text to speech applications, based on neural networks.
  • 15 Apr 2021 1 repository listed
    Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard.
  • 11 Apr 2021 1 repository listed
    Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output.
  • 9 Jan 2021 1 repository listed
    To enable tasks such as search/retrieval and classification over all the available data, we need robust algorithms for text normalization, i. e., for cleaning different kinds of noise in the text.
  • 23 Sep 2020 1 repository listed
    For text normalization, sentence fusion, and grammatical error correction, our approach improves explainability by associating each edit operation with a human-readable tag.
  • 20 Aug 2020 1 repository listed
    Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world.
  • 12 Nov 2019 1 repository listed
    Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications.
  • 1 Nov 2019 1 repository listed
    We compare different LSTMs and transformer models in terms of their effectiveness in normalizing dialectal Finnish into the normative standard Finnish.
  • 12 Apr 2019 1 repository listed
    Social media offer an abundant source of valuable raw data, however informal writing can quickly become a bottleneck for many natural language processing (NLP) tasks.
  • 6 Mar 2019 1 repository listed
    Text normalization is a ubiquitous process that appears as the first step of many Natural Language Processing problems.
  • 31 May 2018 1 repository listed
    We perform text normalization, i. e. the transformation of words from the written to the spoken form, using a memory augmented neural network.
  • 30 Oct 2017 1 repository listed
    The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written.
  • 31 Oct 2016 1 repository listed
    Though our conclusions are largely negative on this point, we are actually not arguing that the text normalization problem is intractable using an pure RNN approach, merely that it is not going to be something that can…
  • 27 Jun 2016 1 repository listed
    Existing corpora for intrinsic evaluation are not targeted towards tasks in informal domains such as Twitter or news comment forums.
  • Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
    30 May 2025 0 repositories listed
    Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability.
  • Visualizing Public Opinion on X: A Real-Time Sentiment Dashboard Using VADER and DistilBERT
    21 Apr 2025 0 repositories listed
    In the age of social media, understanding public sentiment toward major corporations is crucial for investors, policymakers, and researchers.
  • Chain of Correction for Full-text Speech Recognition with Large Language Models
    2 Apr 2025 0 repositories listed
    Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) has gained increased attention due to its potential to correct errors across long contexts and address a broader…
  • Misspellings in Natural Language Processing: A survey
    28 Jan 2025 0 repositories listed
  • Universal-2-TF: Robust All-Neural Text Formatting for ASR
    10 Jan 2025 0 repositories listed
  • Neural Text Normalization for Luxembourgish using Real-Life Variation Data
    12 Dec 2024 0 repositories listed
  • Machine Learning Driven Smishing Detection Framework for Mobile Security
    9 Dec 2024 0 repositories listed
  • Hybrid Deep Learning for Legal Text Analysis: Predicting Punishment Durations in Indonesian Court Rulings
    26 Oct 2024 0 repositories listed
  • WER We Stand: Benchmarking Urdu ASR Models
    17 Sep 2024 0 repositories listed
  • Full-text Error Correction for Chinese Speech Recognition with Large Language Model
    12 Sep 2024 0 repositories listed
  • Historical German Text Normalization Using Type- and Token-Based Language Modeling
    4 Sep 2024 0 repositories listed
  • What is lost in Normalization? Exploring Pitfalls in Multilingual ASR Model Evaluations
    4 Sep 2024 0 repositories listed
  • Is text normalization relevant for classifying medieval charters?
    29 Aug 2024 0 repositories listed
  • Positional Description for Numerical Normalization
    22 Aug 2024 0 repositories listed
  • The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization
    23 Jul 2024 0 repositories listed
  • Exploiting Dialect Identification in Automatic Dialectal Text Normalization
    3 Jul 2024 0 repositories listed
  • Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling
    14 Apr 2024 0 repositories listed
  • Normalization of Lithuanian Text Using Regular Expressions
    29 Dec 2023 0 repositories listed
  • A Chat About Boring Problems: Studying GPT-based text normalization
    23 Sep 2023 0 repositories listed
  • Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Method
    12 Sep 2023 0 repositories listed
  • LDEB -- Label Digitization with Emotion Binarization and Machine Learning for Emotion Recognition in Conversational Dialogues
    3 Jun 2023 0 repositories listed
  • A unified front-end framework for English text-to-speech synthesis
    18 May 2023 0 repositories listed
  • Language Agnostic Data-Driven Inverse Text Normalization
    20 Jan 2023 0 repositories listed
  • 22 Nov 2022 0 repositories listed
  • Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition
    7 Nov 2022 0 repositories listed
  • TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection
    27 Oct 2022 0 repositories listed
  • Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition
    26 Oct 2022 0 repositories listed
  • Singlish Message Paraphrasing: A Joint Task of Creole Translation and Text Normalization
    1 Oct 2022 0 repositories listed
  • Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech
    7 Sep 2022 0 repositories listed
  • Thutmose Tagger: Single-pass neural model for Inverse Text Normalization
    29 Jul 2022 0 repositories listed
  • Improving Data Driven Inverse Text Normalization using Data Augmentation
    20 Jul 2022 0 repositories listed
  • Adversarial Text Normalization
    8 Jun 2022 0 repositories listed
  • Boring Problems Are Sometimes the Most Interesting
    1 Jun 2022 0 repositories listed
  • JHU IWSLT 2022 Dialect Speech Translation System Description
    1 May 2022 0 repositories listed
  • Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
    29 Mar 2022 0 repositories listed
  • Transformer-based Models of Text Normalization for Speech Applications
    1 Feb 2022 0 repositories listed
  • SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
    20 Oct 2021 0 repositories listed
  • A Fast Randomized Algorithm for Massive Text Normalization
    6 Oct 2021 0 repositories listed
  • The Impact of Text Normalization on Multiword Expressions Discovery in Persian
    1 Sep 2021 0 repositories listed
  • A Unified Transformer-based Framework for Duplex Text Normalization
    23 Aug 2021 0 repositories listed
  • BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task
    1 Jun 2021 0 repositories listed
  • Creating Data in Icelandic for Text Normalization
    1 May 2021 0 repositories listed
  • 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
    30 Apr 2021 0 repositories listed
  • Text Normalization for Low-Resource Languages of Africa
    29 Mar 2021 0 repositories listed
  • MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training
    15 Feb 2021 0 repositories listed
  • Neural Inverse Text Normalization
    12 Feb 2021 0 repositories listed
  • hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization
    1 Dec 2020 0 repositories listed
  • Neural text normalization leveraging similarities of strings and sounds
    4 Nov 2020 0 repositories listed
  • Service-oriented Text-to-SQL Parsing
    1 Nov 2020 0 repositories listed
  • TNT: Text Normalization based Pre-training of Transformers for Content Moderation
    1 Nov 2020 0 repositories listed
  • Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning
    19 Sep 2020 0 repositories listed
  • An improved Bayesian TRIE based model for SMS text normalization
    4 Aug 2020 0 repositories listed
  • Neural Multi-task Text Normalization and Sanitization with Pointer-Generator
    1 Jul 2020 0 repositories listed
  • Semi-supervised Contextual Historical Text Normalization
    1 Jul 2020 0 repositories listed
  • Normalizing Text using Language Modelling based on Phonetics and String Similarity
    25 Jun 2020 0 repositories listed
  • Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
    2 Jun 2020 0 repositories listed
  • A Spelling Correction Corpus for Multiple Arabic Dialects
    1 May 2020 0 repositories listed
  • Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech
    1 May 2020 0 repositories listed
  • Data-Driven Parametric Text Normalization: Rapidly Scaling Finite-State Transduction Verbalizers to New Languages
    1 May 2020 0 repositories listed
  • Developing Resources for Automated Speech Processing of Quebec French
    1 May 2020 0 repositories listed
  • Scalable Multilingual Frontend for TTS
    10 Apr 2020 0 repositories listed
  • A hybrid text normalization system using multi-head self-attention for mandarin
    11 Nov 2019 0 repositories listed
  • RNN-T For Latency Controlled ASR With Improved Beam Search
    5 Nov 2019 0 repositories listed
  • Benefits of Data Augmentation for NMT-based Text Normalization of User-Generated Content
    1 Nov 2019 0 repositories listed
  • Unsupervised Neologism Normalization Using Embedding Space Mapping
    1 Nov 2019 0 repositories listed
  • Amharic Text Normalization with Sequence-to-Sequence Models
    25 Sep 2019 0 repositories listed
  • Comparing MT Approaches for Text Normalization
    1 Sep 2019 0 repositories listed
  • Give It a Shot: Few-shot Learning to Normalize ADR Mentions in Social Media Posts
    1 Aug 2019 0 repositories listed
  • Historical Text Normalization with Delayed Rewards
    1 Jul 2019 0 repositories listed
  • Normalizing Non-canonical Turkish Texts Using Machine Translation Approaches
    1 Jul 2019 0 repositories listed
  • Neural Models of Text Normalization for Speech Applications
    1 Jun 2019 0 repositories listed
  • Neural Text Normalization with Subword Units
    1 Jun 2019 0 repositories listed
  • Multilevel Text Normalization with Sequence-to-Sequence Networks and Multisource Learning
    27 Mar 2019 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections