Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task. However, existing retrieval-based EAE methods have two main limitations: (1) input length constraints and (2) the gap between the retriever and the inference model. These issues limit the diversity and quality of the retrieved information. In this paper, we propose a Compressive Memory-based Retrieval (CMR) mechanism for EAE, which addresses the two limitations mentioned above. Our compressive memory, designed as a dynamic matrix that effectively caches retrieved information and supports continuous updates, overcomes the limitations of the input length. Additionally, after pre-loading all candidate demonstrations into the compressive memory, the model further retrieves and filters relevant information from memory based on the input query, bridging the gap between the retriever and the inference model. Extensive experiments show that our method achieves new state-of-the-art performance on three public datasets (RAMS, WikiEvents, ACE05), significantly outperforming existing retrieval-based EAE methods.
AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction
Nara Institute of Science and Technology(奈良先端科学技术大学院大学);National Institute of Information and Communications Technology (NICT)(信息通信研究机构);Kyoto University(京都大学);Kyoto Institute of Technology(京都工艺纤维大学)
Named Entity and Relation Extraction with Multi-Modal Retrieval
ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程研究中心);Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院上海微系统与信息技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Singapore University of Technology and Design(新加坡科技设计大学)
Event Temporal Relation Extraction based on Retrieval-Augmented on LLMs
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis
Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学);The Chinese University of Hong Kong(香港中文大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校);University of Cambridge(剑桥大学)
Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
Nanjing University of Science and Technology(南京理工大学);Northeastern University(东北大学);Singapore Institute of Technology(新加坡理工大学);Singapore University of Technology and Design(新加坡科技设计大学)
AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages
Masakhane NLP;Saarland University(萨尔兰大学);Saarland Informatic Campus(萨尔兰信息学院);National Institute of Informatics(国家信息研究所);University of Waterloo(滑铁卢大学);University College London(伦敦大学学院);Instituto Politécnico Nacional(国家理工学院);University of Ilorin(伊洛林大学);Universidad de Deusto(德尤斯大学);Bayero University(贝亚罗大学);University of Lagos(拉各斯大学);Black Swan(黑天鹅);Addis Ababa University(亚的斯亚贝巴大学);Universite Alioune Diop(阿利乌内·迪普大学);McGill University(麦吉尔大学)
KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities
Nanjing Normal University, School of Computer Science and Electronic Informatics(南京师范大学计算机科学与电子信息学院);State Key Laboratory for Novel Software Technology at Nanjing University(南京大学新型软件技术国家重点实验室);Nanjing University, School of Computer Science(南京大学计算机科学学院)
Aligning Extraction and Generation for Robust Retrieval-Augmented Generation
Meta;Institute for Clarity in Documentation(清晰文档研究所);Inria Paris-Rocquencourt(Inria 巴黎-罗克quencourt 分所);Rajiv Gandhi University(拉朱·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒尔研究实验室)
Query Generation for Patent Retrieval with Keyword Extraction based on Syntactic Features
Amsterdam Business School, University of Amsterdam(阿姆斯特丹大学阿姆斯特丹商学院);European Patent Office(欧洲专利局);Institute of Informatics, University of Amsterdam(阿姆斯特丹大学信息学院)
Learning Dual Retrieval Module for Semi-supervised Relation Extraction
University of Southern California(南加利福尼亚大学);Tsinghua University(清华大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
关系抽取是文本数据内容结构化的一项重要任务,在弱监督学习时变得特别具有挑战性-只有有限数量的标记句子,而大量的未标记句子可用。大多数现有的工作都是基于自我训练的想法来利用未标记的数据(即,自举模型)和多视图学习(例如,集合多个模型变体)。然而,这些方法或者遭受语义漂移的问题,或者没有完全捕获关系抽取的问题特征。在本文中,我们利用一个关键的见解,检索句子表达的关系是一个双重任务的预测关系标签为一个给定的句子-两个任务是互补的,可以共同优化相互增强。为了对这种直觉进行建模,我们提出了DualRE,这是一个原则性的框架,它引入了一个与原始关系预测模块联合训练的检索模块。通过这种方式,检索模块从未标记数据中选择的高质量样本可以用于改进预测模块,反之亦然。在两个公共数据集上的实验结果\footnote{\small Code and data can be found at \url{https://github.com/INK-USC/DualRE}.}以及案例研究证明了DualRE方法的有效性。
Universal Information Extraction with Meta-Pretrained Self-Retrieval
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Xiaomi AI Lab, Xiaomi Inc.(小米公司小米人工智能实验室)
Evaluating LLM Abilities to Understand Tabular Electronic Health Records: A Comprehensive Study of Patient Data Extraction and Retrieval
Université Paul Sabatier(保罗·萨巴蒂埃大学);IRIT(信息论与电信研究所);Centre Hospitalier Universitaire de Toulouse(图卢兹大学医院中心);INSERM(法国国家健康与医学研究院);Université de Toulouse(图卢兹大学);Faculté de Médecine(医学院)
GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extraction
School of Software, Henan University(河南大学软件学院);China Mobile Research Institute(中国移动研究院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
A Hybrid Citation Retrieval Algorithm for Evidence-based Clinical Knowledge Summarization: Combining Concept Extraction, Vector Similarity and Query Expansion for High Precision
Northwestern University Feinberg School of Medicine(西北大学范伯格医学院);Bluhm Cardiovascular Institute of Northwestern Medicine(西北大学布鲁姆心血管研究所);University of Kansas Medical Center(堪萨斯大学医学中心)