A survey of direct speech-to-speech translation models, with a taxonomy of offline, simultaneous, and LLM-based systems and a small new benchmark comparison on CVSS-C.
Bitext Mining for Low-Resource Languages via Contrastive Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Mining high-quality bitexts for low-resource languages is challenging. This paper shows that sentence representation of language models fine-tuned with multiple negatives ranking loss, a contrastive objective, helps retrieve clean bitexts. Experiments show that parallel data mined from our approach substantially outperform the previous state-of-the-art method on low resource languages Khmer and Pashto.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Direct Speech-to-Speech Neural Machine Translation: A Survey
A survey of direct speech-to-speech translation models, with a taxonomy of offline, simultaneous, and LLM-based systems and a small new benchmark comparison on CVSS-C.