Papers with RTT

2 papers
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to generate adversarial examples for NMT use the meaning-preserving restriction.
Approach: They propose a new definition for adversarial examples based on the Doubly Round-Trip Translation (DRTT) they introduce masked language models to construct bilingual adversarials based upon DRTT .
Outcome: The proposed approach significantly improves the robustness of the NMT model on clean and noisy test sets.
Hi-GEC: Hindi Grammar Error Correction in Low Resource Scenario (2025.coling-main)

Copied to clipboard

Challenge: Automated Grammatical Error Correction (GEC) is a scarcely explored low-resource language . a recent study focused on English, but it focused on Hindi, which presents unique challenges due to its complex syntax and intricate morphology.
Approach: They propose to use a human-edited dataset to generate Hindi GEC data . they also investigate round trip translation using diverse languages for the technique .
Outcome: The proposed method outperforms other methods in Hindi, showing that it is highly efficient.

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