Few-shot and zero-shot entity linking focus on the tail and emerging
ent...
The presence of shadows significantly impacts the visual quality of scan...
Multi-modal sarcasm detection has attracted much recent attention.
Never...
Event skeleton generation, aiming to induce an event schema skeleton gra...
Emotion Recognition in Conversation (ERC) across modalities is of vital
...
Open intent classification, which aims to correctly classify the known
i...
Event extraction is a fundamental task in natural language processing th...
Deep learning techniques have dominated the literature on aspect-based
s...
We present Mask-then-Fill, a flexible and effective data augmentation
fr...
We present IBR, an Iterative Backward Reasoning model to solve the proof...
Reviews of songs play an important role in online music service platform...
The goal of empathetic response generation is to enhance the ability of
...
Representations of events described in text are important for various ta...
This ability to learn consecutive tasks without forgetting how to perfor...
Lifelong learning capabilities are crucial for sentiment classifiers to
...
The lack of reliable automatic evaluation metrics is a major impediment ...
Pre-trained language models (e.g., BERT) have achieved significant succe...
Neural network models usually suffer from the challenge of incorporating...
Attention-based neural models were employed to detect the different aspe...
Emotion cause extraction aims to identify the reasons behind a certain
e...