paper-with-me

Papers Document-level Event Extraction

“Document-level Event Extraction” 태그가 달린 논문 32편 · 필터 해제

Are Triggers Needed for Document-Level Event Extraction?

2024-11-13 · Shaden Shaar, Wayne Chen, Maitreyi Chatterjee, Barry Wang 외

Most existing work on event extraction has focused on sentence-level texts and presumes the identification of a trigger-span -- a word or phrase in the input that evokes the occurrence of an event of interest. Event argu…

Document-level Event ExtractionEvent ExtractionSentence

Document-Level Event Extraction with Definition-Driven ICL

2024-08-10 · Zhuoyuan Liu, Yilin Luo

In the field of Natural Language Processing (NLP), Large Language Models (LLMs) have shown great potential in document-level event extraction tasks, but existing methods face challenges in the design of prompts. To addre…

Document-level Event ExtractionEvent ExtractionPrompt Engineering

Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm

2024-06-23 · Qiang Gao, Zixiang Meng, Bobo Li, Jun Zhou 외

Document-level event extraction aims to extract structured event information from unstructured text. However, a single document often contains limited event information and the roles of different event arguments may be b…

coreference-resolutionCoreference ResolutionDocument-level Event ExtractionEvent Extraction

CMNEE: A Large-Scale Document-Level Event Extraction Dataset based on Open-Source Chinese Military News

2024-04-18 · Mengna Zhu, Zijie Xu, Kaisheng Zeng, Kaiming Xiao 외

Extracting structured event knowledge, including event triggers and corresponding arguments, from military texts is fundamental to many applications, such as intelligence analysis and decision assistance. However, event …

Document-level Event ExtractionEvent Extraction

Event-Keyed Summarization

2024-02-10 · William Gantt, Alexander Martin, Pavlo Kuchmiichuk, Aaron Steven White

We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a specific event, given a do…

Document-level Event ExtractionEvent Extraction

Probing Representations for Document-level Event Extraction

2023-10-23 · Barry Wang, Xinya Du, Claire Cardie

The probing classifiers framework has been employed for interpreting deep neural network models for a variety of natural language processing (NLP) applications. Studies, however, have largely focused on sentencelevel NLP…

Document-level Event ExtractionEvent ExtractionProbing Language ModelsSentence

Type-aware Decoding via Explicitly Aggregating Event Information for Document-level Event Extraction

2023-10-16 · Gang Zhao, Yidong Shi, Shudong Lu, Xinjie Yang 외

Document-level event extraction (DEE) faces two main challenges: arguments-scattering and multi-event. Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sent…

Document-level Event ExtractionEvent DetectionEvent Extraction

Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction

2023-06-30 · Qizhi Wan, Changxuan Wan, Keli Xiao, Hui Xiong 외

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. Howe…

Document-level Event ExtractionEvent ExtractionInformation RetrievalRetrieval

基于框架语义映射和类型感知的篇章事件抽取(Document-Level Event Extraction Based on Frame Semantic Mapping and Type Awareness)

2022-10-01 · CCL 2022 10 · Jiang Lu, Ru Li, Xuefeng Su, Zhichao Yan 외

“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。”

Document-level Event ExtractionEvent Extraction

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction

2022-10-01 · COLING 2022 10 · Yubing Ren, Yanan Cao, Fang Fang, Ping Guo 외

Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text. Existing methods struggle in Do…

Document-level Event ExtractionEvent Extraction

Few-Shot Document-Level Event Argument Extraction

2022-09-06 · Xianjun Yang, Yujie Lu, Linda Petzold

Event argument extraction (EAE) has been well studied at the sentence level but under-explored at the document level. In this paper, we study to capture event arguments that actually spread across sentences in documents.…

Document-level Event ExtractionEvent Argument ExtractionEvent ExtractionSentence

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction

2022-07-01 · NAACL 2022 7 · Meihan Tong, Bin Xu, Shuai Wang, Meihuan Han 외

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of docum…

Document-level Event ExtractionEvent ExtractionSentence

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

2022-06-07 · NAACL 2022 7 · Yuan Liang, Zhuoxuan Jiang, Di Yin, Bo Ren

In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multiple events may lie in one document (multi-event issue). In this paper, we argue that the rel…

Document-level Event ExtractionEvent ExtractionMulti-Task LearningRelation+2

A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction

2022-04-30 · NAACL 2022 7 · Runxin Xu, Peiyi Wang, Tianyu Liu, Shuang Zeng 외

Most previous studies aim at extracting events from a single sentence, while document-level event extraction still remains under-explored. In this paper, we focus on extracting event arguments from an entire document, wh…

Abstract Meaning RepresentationDocument-level Event ExtractionEvent Argument ExtractionEvent Extraction+1

Document-Level Event Extraction via Human-Like Reading Process

2022-02-07 · Shiyao Cui, Xin Cong, Bowen Yu, Tingwen Liu 외

Document-level Event Extraction (DEE) is particularly tricky due to the two challenges it poses: scattering-arguments and multi-events. The first challenge means that arguments of one event record could reside in differe…

Document-level Event ExtractionEvent Extraction

Exploiting Coreference and Schema Structure for Document-level Event Extraction

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Document-level event extraction (DEE) extracts structured information of events from a document. Previous studies focus on improving the model architecture. We argue that exploiting data characteristics is also important…

Document-level Event ExtractionEvent Extraction

Writing Style Aware Document-level Event Extraction

2022-01-10 · Zhuo Xu, Yue Wang, Lu Bai, Lixin Cui

Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works discuss this issue with the token-level…

Document-level Event ExtractionEvent ExtractionMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Most previous studies aim at extracting events from a single sentence, while document-level event extraction still remains under-explored. In this paper, we focus on extracting event arguments from an entire document, wh…

Document-level Event ExtractionEvent Argument ExtractionEvent ExtractionSentence

Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph

2021-12-11 · Tong Zhu, Xiaoye Qu, Wenliang Chen, Zhefeng Wang 외

Most previous studies of document-level event extraction mainly focus on building argument chains in an autoregressive way, which achieves a certain success but is inefficient in both training and inference. In contrast …

Document-level Event ExtractionEvent ExtractionGPU

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of docum…

Document-level Event ExtractionEvent ExtractionSentence
1–20 / 32 다음 →