Traditional multitask learning methods basically can only exploit common...
Large-scale Language Models (LLMs) are constrained by their inability to...
Pretrained language models (PLMs) have shown marvelous improvements acro...
Pretrained language models (PLMs) have shown marvelous improvements acro...
Dialogue summarization aims to condense a given dialogue into a simple a...
Massively multi-task learning with large language models has recently ma...
Knowledge distillation (KD) has been widely used for model compression a...
Contrastive learning has become a new paradigm for unsupervised sentence...
Most current multi-modal summarization methods follow a cascaded manner,...
Unsupervised summarization methods have achieved remarkable results by
i...
Most translation tasks among languages belong to the zero-resource
trans...
Relation extraction is a key task in Natural Language Processing (NLP), ...
Pretrained language models (PLMs) trained on large-scale unlabeled corpu...
Confidence estimation aims to quantify the confidence of the model
predi...
This paper presents a Pathways approach to handle many tasks at once. Ou...
The standard BERT adopts subword-based tokenization, which may break a w...
Embedding based methods are widely used for unsupervised keyphrase extra...
Multi-choice Machine Reading Comprehension (MMRC) aims to select the cor...
Due to the highly parallelizable architecture, Transformer is faster to ...
Recently, Transformer has achieved the state-of-the-art performance on m...
Cross-lingual word embeddings aim to capture common linguistic regularit...
Although Neural Machine Translation (NMT) has achieved remarkable progre...
Machine translation has made rapid advances in recent years. Millions of...