no code implementations • 27 Feb 2024 • Xiangqing Shen, Yurun Song, Siwei Wu, Rui Xia
In this work, we draw inspiration from a commonsense knowledge base ConceptNet in natural language processing, and systematically define the types of visual commonsense.
1 code implementation • 24 Jan 2024 • Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin
We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines.
no code implementations • 5 Oct 2023 • Siwei Wu, Xiangqing Shen, Rui Xia
Firstly, EDIT generates open questions related to the dialogue context as the potential user's intention; Then, EDIT answers those questions by interacting with LLMs and searching in domain-specific knowledge bases respectively, and use LLMs to choose the proper answers to questions as extra knowledge; Finally, EDIT enhances response generation by explicitly integrating those extra knowledge.
no code implementations • 2 Aug 2023 • Yonghe Zhao, Qiang Huang, Siwei Wu, Yun Peng, Huiyan Sun
By disentangling observed and unobserved confounders, VLUCI constructs a doubly variational inference model to approximate the distribution of unobserved confounders, which are used for inferring more accurate counterfactual outcomes.
1 code implementation • 29 Jun 2023 • Hongjie Cai, Nan Song, Zengzhi Wang, Qiming Xie, Qiankun Zhao, Ke Li, Siwei Wu, Shijie Liu, Jianfei Yu, Rui Xia
Aspect-based sentiment analysis is a long-standing research interest in the field of opinion mining, and in recent years, researchers have gradually shifted their focus from simple ABSA subtasks to end-to-end multi-element ABSA tasks.
1 code implementation • 26 May 2023 • Siwei Wu, Xiangqing Shen, Rui Xia
To address the two problems, we propose a new CSKG completion framework based on Contrastive Pretraining and Node Clustering (CPNC).
1 code implementation • 14 Oct 2022 • Xiangqing Shen, Siwei Wu, Rui Xia
Both automatic and human evaluation on an annotated subgraph of ATOMIC demonstrate the advantage of Rel-CSKGC over strong baselines.