Pre-trained language models for text generation: A survey
Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …
A survey on non-autoregressive generation for neural machine translation and beyond
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …
(NMT) to speed up inference, has attracted much attention in both machine learning and …
M3p: Learning universal representations via multitask multilingual multimodal pre-training
M Ni, H Huang, L Su, E Cui, T Bharti… - Proceedings of the …, 2021 - openaccess.thecvf.com
We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines
multilingual pre-training and multimodal pre-training into a unified framework via multitask …
multilingual pre-training and multimodal pre-training into a unified framework via multitask …
Improving neural machine translation by bidirectional training
We present a simple and effective pretraining strategy--bidirectional training (BiT) for neural
machine translation. Specifically, we bidirectionally update the model parameters at the …
machine translation. Specifically, we bidirectionally update the model parameters at the …
CROP: zero-shot cross-lingual named entity recognition with multilingual labeled sequence translation
Named entity recognition (NER) suffers from the scarcity of annotated training data,
especially for low-resource languages without labeled data. Cross-lingual NER has been …
especially for low-resource languages without labeled data. Cross-lingual NER has been …
On the complementarity between pre-training and back-translation for neural machine translation
Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize
monolingual data for improving the model performance of neural machine translation (NMT) …
monolingual data for improving the model performance of neural machine translation (NMT) …
End-to-end speech translation for code switched speech
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases
from different languages. CS can pose significant accuracy challenges to NLP, due to the …
from different languages. CS can pose significant accuracy challenges to NLP, due to the …
Multilingual agreement for multilingual neural machine translation
Although multilingual neural machine translation (MNMT) enables multiple language
translations, the training process is based on independent multilingual objectives. Most …
translations, the training process is based on independent multilingual objectives. Most …
Cultural concept adaptation on multimodal reasoning
Z Li, Y Zhang - Proceedings of the 2023 Conference on Empirical …, 2023 - aclanthology.org
Developing cultural adaptation methods is important, which can improve the model
performance on the low-resource ones and provide more equitable opportunities for …
performance on the low-resource ones and provide more equitable opportunities for …
Continual mixed-language pre-training for extremely low-resource neural machine translation
The data scarcity in low-resource languages has become a bottleneck to building robust
neural machine translation systems. Fine-tuning a multilingual pre-trained model (eg …
neural machine translation systems. Fine-tuning a multilingual pre-trained model (eg …