ChatGPT has gained significant interest due to its impressive performanc...
In this paper, we systematically study the potential of pre-training wit...
Dialogue response selection aims to select an appropriate response from
...
News recommendation aims to predict click behaviors based on user behavi...
Passage retrieval aims to retrieve relevant passages from large collecti...
Growing techniques have been emerging to improve the performance of pass...
This paper presents a pre-training technique called query-as-context tha...
Video language pre-training methods have mainly adopted sparse sampling
...
Contrastive learning has been extensively studied in sentence embedding
...
This report presents a comprehensive view of our vision on the developme...
Dense passage retrieval aims to retrieve the relevant passages of a quer...
Cancer survival prediction is important for developing personalized
trea...
Before entering the neural network, a token is generally converted to th...
Contrastive learning has been proven suitable for learning sentence
embe...
While contrastive learning greatly advances the representation of senten...
Contrastive learning has been attracting much attention for learning
uns...
Contrastive learning has been gradually applied to learn high-quality
un...
Due to the frequent murder incidents of ride-hailing drivers in China in...
This paper studies compressing pre-trained language models, like BERT (D...
While several state-of-the-art approaches to dialogue state tracking (DS...
This paper focuses on the task of generating long structured sentences w...
This paper focuses on the task of sentiment transfer on non-parallel tex...
Imbalanced data commonly exists in real world, espacially in
sentiment-r...
We propose a novel data augmentation method for labeled sentences called...
We introduce LUCSS, a language-based system for interactive col- orizati...