Most research about natural language generation (NLG) relies on evaluati...
Training models with varying capacities can be advantageous for deployin...
Gender bias is a significant issue in machine translation, leading to on...
Several recent papers claim human parity at sentence-level Machine
Trans...
While multilingual neural machine translation has achieved great success...
Large language models (LLMs) demonstrate impressive multilingual capabil...
Large language models (LLMs) have shown surprisingly good performance in...
In this work, we study how the generalization performance of a given
dir...
Despite that going deep has proven successful in many neural architectur...
Context-aware neural machine translation aims to use the document-level
...
Pre-trained models have achieved remarkable success in natural language
...
Despite the current success of multilingual pre-training, most prior wor...
Machine translation (MT) has almost achieved human parity at sentence-le...
Named entity recognition (NER) suffers from the scarcity of annotated
tr...
Multilingual machine translation has been proven an effective strategy t...
Transformer structure, stacked by a sequence of encoder and decoder netw...
Multilingual neural machine translation (MNMT) trained in multiple langu...
Most translation tasks among languages belong to the zero-resource
trans...
In this paper, we propose a simple yet effective method to stabilize
ext...
Prompt-based tuning has been proven effective for pretrained language mo...
While end-to-end neural machine translation (NMT) has achieved impressiv...
Existing document-level neural machine translation (NMT) models have
suf...
This report describes Microsoft's machine translation systems for the WM...
This paper demonstrates that multilingual pretraining, a proper fine-tun...
While pretrained encoders have achieved success in various natural langu...
While non-autoregressive (NAR) models are showing great promise for mach...
Previous works mainly focus on improving cross-lingual transfer for NLU ...
Multilingual machine translation enables a single model to translate bet...
Electrocardiogram (ECG) is a widely used reliable, non-invasive approach...
The global pandemic has made it more important than ever to quickly and
...
This paper presents a Multitask Multilingual Multimodal Pre-trained mode...
Data augmentation is an effective performance enhancement in neural mach...
While many BERT-based cross-modal pre-trained models produce excellent
r...
Brain computer interface (BCI) has been popular as a key approach to mon...
Millions of people with severe speech disorders around the world may reg...
Cross-lingual word embeddings aim to capture common linguistic regularit...
Machine translation has made rapid advances in recent years. Millions of...