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 …

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 …

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 …

We present a simple and effective pretraining strategy--bidirectional training (BiT) for neural
machine translation. Specifically, we bidirectionally update the model parameters at the …

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 …

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) …

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 …

Although multilingual neural machine translation (MNMT) enables multiple language
translations, the training process is based on independent multilingual objectives. Most …

Developing cultural adaptation methods is important, which can improve the model
performance on the low-resource ones and provide more equitable opportunities for …

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 …