PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 32-46
Abstract
Alireza Salemi, Amirhossein Abaskohi, Sara Tavakoli, Azadeh Shakery, Yadollah Yaghoobzadeh. Proceedings of the The Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023). 2023.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs2021
- ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization2021
- mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer2021
- Multilingual Denoising Pre-training for Neural Machine TranslationTransactions of the Association for Computational Linguistics, 2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Unsupervised Cross-lingual Representation Learning at Scale2020
- Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences2020
- XNLI: Evaluating Cross-lingual Sentence Representations2018
- A Multilingual Procedure for Dictionary-Based Sentence Alignment1998
- Steps Toward Knowledge-Based Machine TranslationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1981