Papers with normalizer

3 papers
Adversarial Text Normalization (2022.naacl-industry)

Copied to clipboard

Challenge: Text-based adversarial attacks are becoming more commonplace and accessible to general internet users.
Approach: They propose a method that restores baseline performance on attacked content with low computational overhead.
Outcome: The proposed method restores baseline performance on attacked content with low computational overhead.
A Span-based Linearization for Constituent Trees (2020.acl-main)

Copied to clipboard

Challenge: Existing local models have been used to parse constituent trees, but local models can be faster and more efficient.
Approach: They propose a linearization of a constituent tree and a locally normalized model which computes the normalizer on all spans ending with that split point.
Outcome: The proposed model outperforms existing local models and achieves competitive results with global models.
Unicode Normalization and Grapheme Parsing of Indic Languages (2024.lrec-main)

Copied to clipboard

Challenge: Indic writing systems encode words as linear sequences of Unicode characters . authors propose a grapheme parser for Abugida text to normalize inconsistencies .
Approach: They propose a normalizer for normalizing inconsistencies caused by Unicode encoding schemes . grapheme parser for Abugida deconstructs words into visually distinct orthographic syllables .
Outcome: The proposed library is more efficient than the previously used IndicNLP normalizer . it deconstructs words into visually distinct orthographic syllables or complex graphemes .

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