In this paper, we propose Docprompt for document question answering task...
Coordinate denoising is a promising 3D molecular pre-training method, wh...
Self-supervised molecular representation learning is critical for
molecu...
Structured text extraction is one of the most valuable and challenging
a...
Heterogeneous Graph Neural Networks (HGNNs) have gained significant
popu...
Node classification is a substantial problem in graph-based fraud detect...
Identifying high-quality webpages is fundamental for real-world search
e...
Task-agnostic knowledge distillation attempts to address the problem of
...
Recent progress in diffusion models has revolutionized the popular techn...
Recent years have witnessed the rise and success of pre-training techniq...
Recent efforts of multimodal Transformers have improved Visually Rich
Do...
Estimated time of arrival (ETA) prediction, also known as travel time
es...
Relational graph neural networks have garnered particular attention to e...
Pre-trained models (PTMs) have become a fundamental backbone for downstr...
Pre-trained language models have achieved state-of-the-art results in va...
In recent years, owing to the outstanding performance in graph represent...
Pre-trained models have achieved state-of-the-art results in various Nat...
WikiKG90M in KDD Cup 2021 is a large encyclopedic knowledge graph, which...
Pretrained language models (PLMs) such as BERT adopt a training paradigm...
This paper describes the system designed by ERNIE Team which achieved th...
Code switching is a linguistic phenomenon that may occur within a
multil...
Graph convolutional network (GCN) and label propagation algorithms (LPA)...
Recently, pre-trained models have achieved state-of-the-art results in
v...
We present a novel language representation model enhanced by knowledge c...
As the complexity of deep neural networks (DNNs) trend to grow to absorb...