Novel neural models have been proposed in recent years for learning under domain shift.
Most models, however, only evaluate on a single task, on proprietary datasets, or compare …

Lexical normalization is the task of transforming an utterance into its standardized form. This
task is beneficial for downstream analysis, as it provides a way to harmonize (often …

Language model-based pre-trained representations have become ubiquitous in natural
language processing. They have been shown to significantly improve the performance of …

User generated texts on the web are freely-available and lucrative sources of data for
language technology researchers. Unfortunately, these texts are often dominated by …

We compare different LSTMs and transformer models in terms of their effectiveness in
normalizing dialectal Finnish into the normative standard Finnish. As dialect is the common …

We propose MoNoise: a normalization model focused on generalizability and efficiency, it
aims at being easily reusable and adaptable. Normalization is the task of translating texts …

Malay social media text is a text written on social media networks like Twitter. Commonly,
this text comprises nonstandard words, filled with dialects, foreign languages, word …

User-generated text tends to be noisy with many lexical and orthographic inconsistencies,
making natural language processing (NLP) tasks more challenging. The challenging nature …

Lexical normalization, the translation of non-canonical data to standard language, has
shown to improve the performance of manynatural language processing tasks on social …

Norwegian Twitter data poses an interesting challenge for Natural Language Processing
(NLP) tasks. These texts are difficult for models trained on standardized text in one of the two …