检索结果-内蒙古大学图书馆

document-level relation extraction via commonsense knowledge enhanced graph representation learning

APPLIED INTELLIGENCE 2025年第2期55卷 1-13页

作者： Dai, Qizhu Li, Rongzhen Xue, Zhongxuan Li, Xue Zhong, Jiang Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Univ Queensland Sch Informat Technol & Elect Engn Brisbane 4072 Australia

document-level relation extraction (DocRE) aims to reason about complex relational facts among entities by reading, inferring, and aggregating among entities over multiple sentences in a document. Existing studies construct document-level graphs to enrich interactions between entities. However, these methods pay more attention to the entity nodes and their connections, regardless of the rich knowledge entailed in the original *** this paper, we propose a commonsense knowledge enhanced document-level graph representation, called CGDRE, which delves into the semantic knowledge of the original corpus and improves the ability of DocRE. Firstly, we use coreference contrastive learning to capture potential commonsense knowledge. Secondly, we construct a heterogeneous graph to enhance the graph structure information according to the original document and commonsense knowledge. Lastly, CGDRE infers relations on the aggregated graph and uses focal loss to train the model. Remarkably, it is amazing that CGDRE can effectively alleviate the long-tailed distribution problem in DocRE. Experiments on the public datasets DocRED, DialogRE, and MPDD show that CGDRE can significantly outperform other baselines, achieving a significant performance improvement. Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of commonsense knowledge enhanced graph relation representation.

关键词： document-level relation extraction Contrastive learning Commonsense knowledge Graph neural network

来源：评论

学校读者我要写书评

暂无评论

document-level relation extraction Model Based on Boundary Distance Loss and Long-Tail relation Enhancement 21st

Document-Level Relation Extraction Model Based on Boundary D...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Liu, Xin Yilahun, Hankiz Imam, Seyyare Hamdulla, Askar School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Multilingual Information Technology Urumqi830017 China School of National Security Studies Xinjiang University Urumqi830017 China

ISBN: (纸本)9789819601189

In today’s data-driven era, deriving meaningful insights from documents poses a considerable challenge. The task of document-level relation extraction (DocRE) seeks to discern relationships among multiple entities within documents, mirroring real-world scenarios and introducing more complexity than sentence-level relation extraction (SLRE). DocRE encounters issues such as numerous widely dispersed entities, an imbalance between positive and negative instances, and a long-tail distribution of relation types. We introduce a model for document-level relation extraction that utilizes boundary distance loss and long-tail relation enhancement to tackle these challenges. This approach adeptly captures intricate interactions among entities, enhancing multi-relation extraction performance. Our model achieved improvements of 3.22% and 3.15% in F1 and Ign-F1 scores on the RE-DocRED dataset, respectively. Moreover, it significantly surpasses recent strong baseline models on the JacRED dataset. The experimental results confirm the model’s effectiveness and generalizability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Boundary distance adaptive threshold loss document-level relation extraction Long-tail relationship enhancement Multi-relation extraction

来源：评论

学校读者我要写书评

暂无评论

Improving inference via rich path information and logic rules for document-level relation extraction

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2025年第5期67卷 4207-4231页

作者： Su, Huizhe Xie, Shaorong Yu, Hang Yuan, Changsen Wang, Xinzhi Luo, Xiangfeng Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Beijing Inst Technol Sch Comp Sci & Technol Beijing 100876 Peoples R China

The task of document-level relation extraction is the classification of the relations between pairs of entities within a document. The identification of relations between inter-sentence entity pairs is one of the main challenges, as there may be no direct connections between the entities. Previous researches have attempted to address this challenge by leveraging path information between entities in the graph to predict their relations. However, these methods ignore the insufficiency of relations information in the existing paths and the absence of connecting paths between entity pairs. In this paper, we propose an effective inference model that enhances inter-sentence reasoning at both the document and global levels. Our model enhances path information by aggregating features from various sources along the logical reasoning paths between entities within each document. Additionally, the model learns relational inference rules from large graphs created from multiple documents and applies these rules to enrich existing relational knowledge. The experimental results indicate that our model outperforms existing models on three widely used benchmark datasets. Moreover, further analysis highlights that our model is especially effective in document-level relation extraction, particularly for inter-sentence relation extraction.

关键词： document-level relation extraction Logical reason Inter-sentence inference Entity co-occurrence graph Rule-based inference

来源：评论

学校读者我要写书评

暂无评论

TDGI: Translation-Guided Double-Graph Inference for document-level relation extraction

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第4期47卷 2647-2659页

作者： Zhang, Lingling Zhong, Yujie Zheng, Qinghua Liu, Jun Wang, Qianying Wang, Jiaxin Chang, Xiaojun Xi An Jiao Tong Univ Sch Comp Sci & Technol Key Lab Intelligent Networks Minist Educ Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Comp Sci & Technol Shaanxi Prov Key Lab Big Data Knowledge Engn Xian 710049 Peoples R China Lenovo Res Beijing 100094 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China MBZUAI Dept Comp Vis Abu Dhabi U Arab Emirates

document-level relation extraction (DocRE) aims at predicting relations of all entity pairs in one document, which plays an important role in information extraction. DocRE is more challenging than previous sentence-level relation extraction, as it often requires coreference and logical reasoning across multiple sentences. Graph-based methods are the mainstream solution to this complex reasoning in DocRE. They generally construct the heterogeneous graphs with entities, mentions, and sentences as nodes, co-occurrence and co-reference relations as edges. Their performance is difficult to further break through because the semantics and direction of the relation are not jointly considered in graph inference process. To this end, we propose a novel translation-guided double-graph inference network named TDGI for DocRE. On one hand, TDGI includes two relation semantics-aware and direction-aware reasoning graphs, i.e., mention graph and entity graph, to mine relations among long-distance entities more explicitly. Each graph consists of three elements: vectorized nodes, edges, and direction weights. On the other hand, we devise an interesting translation-based graph updating strategy that guides the embeddings of mention/entity nodes, relation edges, and direction weights following the specific translation algebraic structure, thereby to enhance the reasoning skills of TDGI. In the training procedure of TDGI, we minimize the relation multi-classification loss and triple contrastive loss together to guarantee the model's stability and robustness. Comprehensive experiments on three widely-used datasets show that TDGI achieves outstanding performance comparing with state-of-the-art baselines.

关键词： Cognition Translation Semantics Transformers Data mining Electronic mail Context modeling Vectors Training Robustness document-level relation extraction double-graph inference translation rule relation semantics relation direction

来源：评论

学校读者我要写书评

暂无评论

Path-Aware Reasoning Network for document-level relation extraction with co-regularization loss

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Yin, Yuan Ai, Xuhua Yu, Yiting Qu, Xiaoye Wei, Wei Guangxi Power Grid Co Ltd Nanning Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Cognit Comp & Intelligent Informat Proc CCIIP Lab Wuhan Peoples R China

document-level relation extraction (DocRE) aims to identify complicated relations among entity pairs in a document. It is challenging as a document usually has multiple entity pairs, and the two entities within a pair may also be scattered in a document with different entity-specific labels, even over along distance. Existing works usually focus on extracting crucial evidence sentences as a concise clue for relation inference. However, they suffer from two limitations: (1) indiscriminately utilizing all words in the sentences for relation inference may inevitably introduce noise problems (e.g., unrelated chunks/clauses involved), thus incurring a decline in performance. (2) they do not consider the noisy labeling phenomenon, as there exists a considerable amount of unlabeled instances in the DocRE scenario. To address the above issues, we propose a novel approach, named P ath-Aware R easoning N etwork (PARN) for DocRE. Specifically, PARN explicitly models the shortest inferring paths for each given entity pair over a word-level constructed document graph, and then incorporates a path-aware constraint into the self-attention mechanism, thereby directing the model's attention towards the crucial segments along these paths. Furthermore, a co-regularization loss is also proposed to alleviate the intrinsic noisy labeling problem, which increases the prediction consistency of the output. Extensive experiments on three DocRE datasets demonstrate the superiority of the proposed model, as compared to previous state-of-the-art methods.

关键词： document-level relation extraction Reasoning path Key information detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing document-level relation extraction with Entity Pronoun Resolution and relation Correlation 13th

Enhancing Document-Level Relation Extraction with Entity Pro...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Pi, Qiankun Lu, Jicang Sun, Yepeng Zhu, Taojie Xia, Yi Yang, Chenguang State Key Lab Math Engn & Adv Comp Zhengzhou Henan Peoples R China

ISBN: (纸本)9789819794331;9789819794348

The task of document-level relation extraction aims to identify the semantic relationships between entities in a document. However, the common pronoun ambiguity problem in documents is often not fully considered, resulting in serious issues of unclear pronoun reference in the document itself. In addition, a group of entity pairs may contain multiple relationships, making the task of relation extraction more challenging. In this paper, we propose a new model, EPRRC, to address the above challenges by implementing pronoun resolution and enhancing relation correlation. Specifically, we construct prompts for Large Language Models (LLMs) to achieve pronoun resolution and enhance the completeness of entity information. Ultimately, we obtain the pronoun enhanced dataset PR-DocRED. Then, in the relation filter module, we effectively identify the potential multiple relations between entities based on prior knowledge of relation co-occurrences. The experimental results indicate that our proposed PR-DocRED dataset exhibits significant performance improvements across many model tests. Moreover, the EPRRC model outperforms numerous strong baselines in fundamental evaluations.

关键词： document-level relation extraction LLMs Pronoun resolution relation filter

来源：评论

学校读者我要写书评

暂无评论

Dependency-augmented graph aggregation networks for document-level relation extraction with cross-sentence semantics

引用

Journal of King Saud University - Computer and Information Sciences 2025年第3期37卷 1-12页

作者： Che, Shasha He, Qing Yang, Zhihao Li, Yanbo Du, Nisuo College of Big Data and Information Engineering Guizhou University Guiyang China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China

Finding semantic relationships between words in several sentences is the goal of document-level relation extraction (DocRE), a crucial problem in natural language processing. Current research is unable to accurately characterize long-range interdependence and cross-sentence interactions, which restricts their capacity to capture document-level semantics. In order to alleviate this issue, we introduce the Dependency-Augmented Graph Aggregation Network(DAGA), which is a novel DocRE model. In particular, we design a Dependency Graph Aggregation Module (DGAM) that integrates Sentence Related Graph and Dependency Structure Graph to explore both local and global relational patterns. To explicitly capture document-level sentence-related dependencies and semantic interactions, we propose Dependency-Augmented Attention Mechanism (DAAM). Results from experiments show that our suggested approach improves the F1 score by 1.39 and the Ign F1 score by 1.52 on publicly available benchmark datasets. In summary, DAGA demonstrates higher performance in dealing with complicated semantic relationships at the document level. © The Author(s) 2025.

关键词： Cross-sentence relationships Dependency structure graph document-level relation extraction Multi-head attention Semantic relations

来源：评论

学校读者我要写书评

暂无评论

EMGE: Entities and Mentions Gradual Enhancement with semantics and connection modelling for document-level relation extraction

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Chen, Guojun Chen, Panfeng Wang, Qi Li, Hui Zhou, Xin Wang, Xibin Yu, Aihua Deng, Xingzhi Guizhou Univ State Key Lab Publ Big Data Guiyang 550025 Guizhou Peoples R China GuiZhou Univ Dept Comp Sci & Technol Guiyang 550025 Guizhou Peoples R China Guizhou Inst Technol Sch Data Sci Guiyang 550003 Guizhou Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China

relation extraction is the process of identifying connections between entities in unstructured text and is a critical component of entity-centred information extraction to uncover latent knowledge structures in complex documents. Although graph-based methods have pushed the state-of-the-art forward in relation extraction, current approaches still exhibit limitations. These include incomplete capture of graph structural features, inadequate modelling of long-distance dependencies and imprecise representation of complex entity interactions. A novel E ntities and M entions G radual E nhancement framework called EMGE is proposed. It integrates both contextual and structural information to robustly enhance entity representations for document- level relation extraction. It comprises three primary components: 1) a dynamic relation aware enhancement mechanism to comprehensively encode graph structural features;2) a multi-scale feature enhancement module to effectively capture long-distance dependencies;and 3) an entity-mention pair enhancement mechanism to yield precise representations of classification targets. Extensive empirical evaluation on five widely-adopted datasets demonstrates that EMGE achieves promising performance. Particularly noteworthy are the substantial gains obtained on the challenging CDR dataset, where EMGE achieved relative improvements of 1.5%, 8.8%, and 3.5% over the strongest baseline in terms of the Intra-F1, Inter-F1 and Overall-F1 metrics, respectively. Further experimental results demonstrate that the proposed model outperforms the popular large language model in relation extraction tasks. Our code is available on github.1

关键词： document-level relation extraction Graph structures Long-distance dependency Knowledge enhancement

来源：评论

学校读者我要写书评

暂无评论

Evidence and Axial Attention Guided document-level relation extraction

引用

COMPUTER SPEECH AND LANGUAGE 2025年 90卷

作者： Yuan, Jiawei Leng, Hongyong Qian, Yurong Chen, Jiaying Ma, Mengnan Hou, Shuxiang Xinjiang Univ Sch Software Urumqi 830000 Peoples R China Xinjiang Univ Sch Informat Sci & Engn Urumqi Peoples R China Key Lab Signal Detect & Proc Xinjiang Uygur Autono Urumqi Peoples R China Xinjiang Univ Key Lab Software Engn Urumqi Peoples R China Beijing Inst Technol Sch Comp Sci & Technol BIT Beijing 100081 Peoples R China

document-level relation extraction (DocRE) aims to identify semantic relations among multiple entity pairs within a document. Most of the previous DocRE methods take the entire document as input. However, for human annotators, a small subset of sentences in the document, namely the evidence, is sufficient to infer the relation of an entity pair. Additionally, a document usually contains multiple entities, and these entities are scattered throughout various location of the document. Previous models use these entities independently, ignore the global interdependency among relation triples. To handle above issues, we propose a novel framework EAAGRE (Evidence and Axial Attention Guided relation extraction). Firstly, we use human-annotated evidence labels to supervise the attention module of DocRE system, making the model pay attention to the evidence sentences rather than others. Secondly, we construct an entity-level relation matrix and use axial attention to capture the global interactions among entity pairs. By doing so, we further extract the relations that require multiple entity pairs for prediction. We conduct various experiments on DocRED and have some improvement compared to baseline models, verifying the effectiveness of our model.

关键词： Information extraction document-level relation extraction Evidence retrieval Axial attention

来源：评论

学校读者我要写书评

暂无评论

Mention Distance-aware Interactive Attention with Multi-step Reasoning for document-level relation extraction

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 141卷

作者： Zhang, Fu Wang, Jiapeng Xu, Huangming Wu, Honglin Cheng, Jingwei Li, Weijun North Minzu Univ Sch Comp Sci & Engn Yinchuan 750021 Peoples R China Northeastern Univ Sch Comp Sci & Engn Shenyang 110169 Peoples R China

document-level relation extraction (DocRE) is widely used in various natural language processing and artificial intelligence applications, aiming to identify relations between entities in a document that may appear multiple times or span multiple sentences. Previous methods have relied on global document features to generate a unified representation for each entity, which may result in the loss of entity-specific information and fail to capture the nuanced relations between different entity pairs. In this paper, we propose the M ention D istance-aware I nteractive A ttention with M ulti-step R easoning (MDIAMR) model, which leverages attention mechanisms and graph neural networks to address these challenges. Specifically, we introduce an entity interaction attention module to explicitly model the distance information between mentions and dynamically aggregate all mentions of each entity. This approach highlights the importance of different mentions to the entity, thereby enhancing the entity's representation. Additionally, we design a multi-step reasoning module based on graph attention networks (GAT), which iteratively updates entity pair representations by considering information from neighboring pairs. We also incorporate a cosine similarity loss function to help the model differentiate between entity pairs that are related or unrelated to the target entity pair. Experimental results demonstrate that our model outperforms competitive baseline models on two publicly available datasets.

关键词： document-level relation extraction Mention distance Multi-step reasoning Graph attention network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：