no code implementations • CCL 2022 • Jiang Lu, Ru Li, Xuefeng Su, Zhichao Yan, Jiaxing Chen
“篇章事件抽取是从给定的文本中识别其事件类型和事件论元。目前篇章事件普遍存在数据稀疏和多值论元耦合的问题。基于此, 本文将汉语框架网(CFN)与中文篇章事件建立映射, 同时引入滑窗机制和触发词释义改善了事件检测的数据稀疏问题;使用基于类型感知标签的多事件分离策略缓解了论元耦合问题。为了提升模型的鲁棒性, 进一步引入对抗训练。本文提出的方法在DuEE-Fin和CCKS2021数据集上实验结果显著优于现有方法。”
no code implementations • CCL 2020 • Xiaohui Wang, Ru Li, Zhiqiang Wang, Qinghua Chai, Xiaoqi Han
框架语义角色标注(Frame Semantic Role Labeling, FSRL)是基于FrameNet标注体系的语义分析任务。语义角色标注通常对句法有很强的依赖性, 目前的语义角色标注模型大多基于双向长短时记忆网络Bi-LSTM, 虽然可以获取句子中的长距离依赖信息, 但无法很好获取句子中的句法信息。因此, 引入self-attention机制来捕获句子中每个词的句法信息。实验结果表明, 该模型在CFN(Chinese FrameNet, 汉语框架网)数据集上的F1达到83. 77%, 提升了近11%。
no code implementations • EMNLP 2021 • Yong Guan, Shaoru Guo, Ru Li, XiaoLi Li, Hu Zhang
Recently graph-based methods have been adopted for Abstractive Text Summarization.
no code implementations • EMNLP 2021 • Yong Guan, Shaoru Guo, Ru Li, XiaoLi Li, Hongye Tan
In this paper, we propose a novel Frame Semantic-Enhanced Sentence Modeling for Extractive Summarization, which leverages Frame semantics to model sentences from both intra-sentence level and inter-sentence level, facilitating the text summarization task.
1 code implementation • 11 Dec 2024 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Ru Li, Jeff Z. Pan
To address these issues, we propose a Multi-level Matching network for Multimodal Entity Linking (M3EL).
no code implementations • 22 Oct 2024 • Zhichao Yan, Jiapu Wang, Jiaoyan Chen, XiaoLi Li, Ru Li, Jeff Z. Pan
Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a given question.
no code implementations • 26 Sep 2024 • Qi Zhang, He Wang, Ru Li, Wenbin Li
By identifying and excluding dynamic elements from the mapping process, this segmentation enables the creation of a dense 3D map that accurately represents the static background only.
1 code implementation • 23 Jul 2024 • Jinting Luo, Ru Li, Chengzhi Jiang, XiaoMing Zhang, Mingyan Han, Ting Jiang, Haoqiang Fan, Shuaicheng Liu
Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images.
no code implementations • 22 May 2024 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs.
no code implementations • 11 May 2024 • Yong Guan, Dingxiao Liu, Jinchen Ma, Hao Peng, Xiaozhi Wang, Lei Hou, Ru Li
Inspired by this, we propose Event GDR, an event-centric generative document retrieval model, integrating event knowledge into this task.
no code implementations • 19 Apr 2024 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs).
no code implementations • 15 Apr 2024 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
This paper proposes the HyperMono model for hyper-relational knowledge graph completion, which realizes stage reasoning and qualifier monotonicity.
no code implementations • 5 Mar 2024 • YaoDan Zhang, Zidong Wang, Ru Jia, Ru Li
Compared with the general metric learning model MetricF, the prediction error is reduced by 7. 29%.
no code implementations • 29 Jan 2024 • Yong Guan, Freddy Lecue, Jiaoyan Chen, Ru Li, Jeff Z. Pan
Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts.
1 code implementation • 14 Dec 2023 • Ru Li, Jia Liu, Guanghui Liu, Shengping Zhang, Bing Zeng, Shuaicheng Liu
We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output.
no code implementations • 16 Nov 2023 • Wei zhang, Dai Li, Chen Liang, Fang Zhou, Zhongke Zhang, Xuewei Wang, Ru Li, Yi Zhou, Yaning Huang, Dong Liang, Kai Wang, Zhangyuan Wang, Zhengxing Chen, Fenggang Wu, Minghai Chen, Huayu Li, Yunnan Wu, Zhan Shu, Mindi Yuan, Sri Reddy
To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models.
1 code implementation • 18 Oct 2023 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
Knowledge graph entity typing (KGET) aims at inferring plausible types of entities in knowledge graphs.
1 code implementation • ICCV 2023 • Ting Jiang, Chuan Wang, Xinpeng Li, Ru Li, Haoqiang Fan, Shuaicheng Liu
In this paper, we introduce a new approach for high-quality multi-exposure image fusion (MEF).
1 code implementation • 12 Aug 2023 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
Hyper-relational knowledge graph completion (HKGC) aims at inferring unknown triples while considering its qualifiers.
no code implementations • 10 Apr 2023 • Ru Li, Guanghui Liu, Bing Zeng, Shuaicheng Liu
The method combines the efficiency of optical flow and the accuracy of PatchMatch.
1 code implementation • ICCV 2023 • Suyi Chen, Hao Xu, Ru Li, Guanghui Liu, Chi-Wing Fu, Shuaicheng Liu
We design SIRA-PCR, a new approach to 3D point cloud registration.
1 code implementation • 20 Oct 2022 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, Ru Li, Jeff Z. Pan
We investigate the knowledge graph entity typing task which aims at inferring plausible entity types.
1 code implementation • 2 May 2022 • Zhiwei Hu, Víctor Gutiérrez-Basulto, Zhiliang Xiang, XiaoLi Li, Ru Li, Jeff Z. Pan
Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information.
no code implementations • ACL 2021 • Xuefeng Su, Ru Li, XiaoLi Li, Jeff Z. Pan, Hu Zhang, Qinghua Chai, Xiaoqi Han
In this paper, we propose a Knowledge-Guided Frame Identification framework (KGFI) that integrates three types frame knowledge, including frame definitions, frame elements and frame-to-frame relations, to learn better frame representation, which guides the KGFI to jointly map target words and frames into the same embedding space and subsequently identify the best frame by calculating the dot-product similarity scores between the target word embedding and all of the frame embeddings.
no code implementations • 3 Feb 2021 • Ru Li, Chuan Wang, Jue Wang, Guanghui Liu, Heng-Yu Zhang, Bing Zeng, Shuaicheng Liu
The ground truth images play a leading role in generating reasonable HDR images.
no code implementations • 19 Jan 2021 • Ru Li, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng
We design a multi-task pipeline that includes, (1) a classification branch to classify jigsaw permutations, and (2) a GAN branch to recover features to images in correct orders.
no code implementations • COLING 2020 • Shaoru Guo, Yong Guan, Ru Li, XiaoLi Li, Hongye Tan
Machine reading comprehension (MRC) is one of the most critical yet challenging tasks in natural language understanding(NLU), where both syntax and semantics information of text are essential components for text understanding.
Machine Reading Comprehension
Natural Language Understanding
no code implementations • ACL 2020 • Shaoru Guo, Ru Li, Hongye Tan, Xiao-Li Li, Yong Guan, Hongyan Zhao, Yueping Zhang
Sentence representation (SR) is the most crucial and challenging task in Machine Reading Comprehension (MRC).