Deep-Learning-Based Pre-training and Refined Tuning for Web Summarization Software

M Liu, Z Ma, J Li, YC Wu, X Wang - IEEE Access, 2024 - ieeexplore.ieee.org
In the digital age, the rapid growth of web information has made it increasingly challenging
for individuals and organizations to effectively explore and extract valuable insights from the …

Claret: Pre-training a correlation-aware context-to-event transformer for event-centric generation and classification

Y Zhou, T Shen, X Geng, G Long, D Jiang - arXiv preprint arXiv …, 2022 - arxiv.org
Generating new events given context with correlated ones plays a crucial role in many event-
centric reasoning tasks. Existing works either limit their scope to specific scenarios or …

Tsvfn: Two-stage visual fusion network for multimodal relation extraction

Q Zhao, T Gao, N Guo - Information Processing & Management, 2023 - Elsevier
Multimodal relation extraction is a critical task in information extraction, aiming to predict the
class of relations between head and tail entities from linguistic sequences and related …

Self-supervised logic induction for explainable fuzzy temporal commonsense reasoning

B Cai, X Ding, Z Sun, B Qin, T Liu, L Shang - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Understanding temporal commonsense concepts, such as times of occurrence and
durations is crucial for event-centric language understanding. Reasoning about such …

KRACL: Contrastive learning with graph context modeling for sparse knowledge graph completion

Z Tan, Z Chen, S Feng, Q Zhang, Q Zheng… - Proceedings of the …, 2023 - dl.acm.org
Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional
spaces and have become the de-facto standard for knowledge graph completion. Most …

Multimodal event transformer for image-guided story ending generation

Y Zhou, G Long - arXiv preprint arXiv:2301.11357, 2023 - arxiv.org
Image-guided story ending generation (IgSEG) is to generate a story ending based on given
story plots and ending image. Existing methods focus on cross-modal feature fusion but …

Optimizing search advertising strategies: Integrating reinforcement learning with generalized second-price auctions for enhanced ad ranking and bidding

C Zhou, Y Zhao, J Cao, Y Shen, J Gao, X Cui… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper explores the integration of strategic optimization methods in search advertising,
focusing on ad ranking and bidding mechanisms within E-commerce platforms. By …

Enhancing Narrative Commonsense Reasoning With Multilevel Causal Knowledge

F Mu, W Li - IEEE Transactions on Neural Networks and …, 2024 - ieeexplore.ieee.org
Narratives is an account of the unfolding of events, along with explanations of how and why
these processes and events came to be. To understand narratives, causality has been …

Improving cross-modal alignment for text-guided image inpainting

Y Zhou, G Long - arXiv preprint arXiv:2301.11362, 2023 - arxiv.org
Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in
a damaged image. Existing methods are based on a strong vision encoder and a cross …

Length-Aware Multi-Kernel Transformer for Long Document Classification

G Han, J Tsao, X Huang - arXiv preprint arXiv:2405.07052, 2024 - arxiv.org
Lengthy documents pose a unique challenge to neural language models due to substantial
memory consumption. While existing state-of-the-art (SOTA) models segment long texts into …