Multilingual Pre-Trained Representations
Related Papers
Knowledge Distillation for Quality Estimation
Quality Estimation (QE) is the task of automat- ically predicting Machine Translation quality in the absence of reference translations, mak- ing it applicable in real-time settings, such as translating online …...
Persian Natural Language Inference: A Meta-learning Approach
AbstractIncorporating information from other languages can improve the results of tasks in low-resource languages. A powerful method of building functional natural language processing systems for low-resource languages is to combine …...
Supervised Contrastive Learning for Cross-lingual Transfer Learning
Abstract“Multilingual pre-trained representations are not well-aligned by nature, which harms their performance on cross-lingual tasks. Previous methods propose to post-align the multilingual pretrained representations by multi-view alignment or contrastive learning. …...
Translation Error Detection as Rationale Extraction
AbstractRecent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results in predicting the overall quality of translated sentences. However, detecting specifically which translated words are …...