Challenge: a study using non-canonical text normalization shows that it can surpass the current best performing system by a large margin.
Approach: They propose a fully automated, context-aware machine translation approach with fewer stages of processing.
Outcome: The proposed approach surpasses the current best-performing system by a large margin . the proposed method is more data-hungry and more data sensitive than other methods .

Similar Papers

Synthetic Data for English Lexical Normalization: How Close Can We Get to Manually Annotated Data? (2020.lrec-1)

Copied to clipboard

Challenge: Social media data is a valuable data resource for natural language processing tasks.
Approach: They propose to adapt input text to a more standard form, a task also referred to as normalization.
Outcome: The proposed system scores 94.29 accuracy on the test data compared to 95.22 when trained on human-annotated data.
A Taxonomy for In-depth Evaluation of Normalization for User Generated Content (L18-1)

Copied to clipboard

Challenge: Existing taxonomies for lexical normalization are not suitable for the task of normalization since the categories are substantially different.
Approach: They propose a taxonomy of error categories for lexical normalization . they annotate a recent normalization dataset and read a near-perfect agreement .
Outcome: The proposed taxonomy is based on a recent normalization dataset and it performs well.
Dialect-to-Standard Normalization: A Large-Scale Multilingual Evaluation (2023.findings-emnlp)

Copied to clipboard

Challenge: Text normalization is a range of tasks that consist in replacing non-standard spellings with their standard equivalents.
Approach: They introduce dialect-to-standard normalization as a sentence-level character transduction task and provide a large-scale analysis of these methods.
Outcome: The proposed model performs best for Finnish, Swiss German and Slovene while the pre-trained model using full sentences performs the best for Norwegian.
Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems (2021.naacl-industry)

Copied to clipboard

Challenge: Developing Text Normalization systems for Text-to-Speech (TTS) on new languages is hard.
Approach: They propose a novel architecture to facilitate Text Normalization systems for TTS on new languages . they use a granular tokenization mechanism that enables the system to learn majority of classes .
Outcome: The proposed architecture performs comparable with the state-of-the-art systems on English . the proposed system learns most classes from training data and precodes them for other classes .
An In-depth Analysis of the Effect of Lexical Normalization on the Dependency Parsing of Social Media (D19-55)

Copied to clipboard

Challenge: Existing natural language processing tools are focused on standard texts, but performance drops when used on a different domain.
Approach: They analyze the effect of manual and automatic lexical normalization for dependency parsing . they conclude that automatic normalization scores close to manually annotated normalization .
Outcome: The proposed approach improves performance on social media data for many tasks . it is unclear which replacements have the most impact and what weaknesses exist in the system .
Text Normalization Infrastructure that Scales to Hundreds of Language Varieties (L18-1)

Copied to clipboard

Challenge: a multi-language text normalization infrastructure is used to train language models for keyboards and speech recognition systems.
Approach: They describe a multi-language text normalization infrastructure that prepares textual data to train language models used in Google's keyboards and speech recognition systems.
Outcome: The proposed system can normalize training data across hundreds of languages . it can detect errors in training data and detect corruption issues .
PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech (2025.emnlp-industry)

Copied to clipboard

Challenge: Text Normalization (TN) is a key preprocessing step in Text-to-Speech systems.
Approach: They propose a prompt-based approach to TN using Large Language Models (LLMs) they propose scalable experimentation across languages to reduce the reliance on manual rules .
Outcome: The proposed approach reduces the reliance on manual rules and enables broader linguistic applicability with minimal human intervention across eight languages.
Data and Representation for Turkish Natural Language Inference (2020.emnlp-main)

Copied to clipboard

Challenge: Large annotated datasets in NLP are overwhelmingly in English . obtaining new annotation resources for each task in each language would be prohibitively expensive .
Approach: They propose to use machine translation to translate large annotated datasets into Turkish . they find that in-language embeddings are essential and morphological parsing can be avoided .
Outcome: The proposed model trains on human-translated evaluation sets.
Normalization of Indonesian-English Code-Mixed Twitter Data (D19-55)

Copied to clipboard

Challenge: Twitter is an excellent source of textual data for NLP researches, but it is noisy and often contains typos, slang terms, and non-standard abbreviations.
Approach: They propose a standardization system for Indonesian-English code-mixed Twitter data that includes tokenization, language identification, lexical normalization, and translation.
Outcome: The proposed standardization system is based on four modules for tokenization, language identification, lexical normalization, and translation.
Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data (D19-55)

Copied to clipboard

Challenge: a new corpus of unstructured data from social media is presenting challenges to NLP research . standardisation is neither natural nor universal, it is rather a human invention.
Approach: They compile a parallel corpus of Arabic textual data matched with human annotations . they use a deep neural model designed to deal with context-dependent spelling correction .
Outcome: The proposed model performs best with two CNN sub-network encoders and an LSTM decoder . pre-processing data token-by-token with edit-distance aligner significantly improves performance .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations