The standard definition generation task requires to automatically produc...
Recent years have witnessed increasing interests in prompt-based learnin...
Previous works on emotion recognition in conversation (ERC) follow a two...
Heart failure remains a major public health challenge with growing costs...
The mainstream of the existing approaches for video prediction builds up...
Recently, pre-trained transformer-based models have achieved great succe...
US Census Bureau (USCB) has implemented a new privacy-preserving disclos...
Skeleton-based human action recognition is a longstanding challenge due ...
Existing commonsense knowledge bases often organize tuples in an isolate...
Excellent performance has been achieved on instance segmentation but the...
Despite video forecasting has been a widely explored topic in recent yea...
A simile is a figure of speech that directly makes a comparison, showing...
To model diverse responses for a given post, one promising way is to
int...
Although occlusion widely exists in nature and remains a fundamental
cha...
To sustain engaging conversation, it is critical for chatbots to make go...
We propose a chatbot, namely Mocha to make good use of relevant entities...
In this paper, we implement two state-of-art continuous reinforcement
le...
We develop a high-quality multi-turn dialog dataset, DailyDialog, which ...
Deep latent variable models have been shown to facilitate the response
g...
Despite the successes in capturing continuous distributions, the applica...
Although Generative Adversarial Networks achieve state-of-the-art result...
Query relevance ranking and sentence saliency ranking are the two main t...
Distributed word representations are very useful for capturing semantic
...