Although the pre-training followed by fine-tuning paradigm is used
exten...
Lyrics generation is a well-known application in natural language genera...
Simile detection is a valuable task for many natural language processing...
In recent years, 3D representation learning has turned to 2D vision-lang...
Negative sampling plays a crucial role in training successful sequential...
Pre-trained language models (PLMs) have played an increasing role in
mul...
Prompt learning is a new paradigm for utilizing pre-trained language mod...
The standard paradigm of neural language generation adopts maximum likel...
As a fine-grained and local expression behavior measurement, facial acti...
Despite advances in generating fluent texts, existing pretraining models...
Simile interpretation (SI) and simile generation (SG) are challenging ta...
Since 2017, the Transformer-based models play critical roles in various
...
Although Transformers with fully connected self-attentions are powerful ...
Recently, tuning the pre-trained language model (PLM) in a
parameter-eff...
Vision-and-language pre-trained models (VLMs) have achieved tremendous
s...
Recently, a variety of neural models have been proposed for lyrics
gener...
Unsupervised domain adaptation (UDA) with pre-trained language models (P...
Generating stylized responses is essential to build intelligent and enga...
Recent advances in open-domain dialogue systems rely on the success of n...
Endowing dialogue systems with personas is essential to deliver more
hum...