检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

42 篇 期刊文献
32 篇 会议

馆藏范围

74 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

73 篇 工学
- 71 篇 计算机科学与技术...
- 12 篇 电气工程
- 6 篇 软件工程
- 5 篇 信息与通信工程
- 5 篇 控制科学与工程
- 2 篇 生物医学工程（可授...
- 1 篇 机械工程
- 1 篇 交通运输工程
- 1 篇 生物工程
10 篇 管理学
- 6 篇 管理科学与工程(可...
- 2 篇 公共管理
- 2 篇 图书情报与档案管...
8 篇 医学
- 4 篇 基础医学(可授医学...
- 3 篇 临床医学
- 2 篇 公共卫生与预防医...
- 2 篇 特种医学
- 1 篇 医学技术（可授医学...
7 篇 理学
- 4 篇 数学
- 2 篇 物理学
- 1 篇 化学
- 1 篇 生物学
- 1 篇 系统科学
- 1 篇 统计学（可授理学、...
2 篇 文学
- 2 篇 外国语言文学

主题

74 篇 document-level r...
10 篇 information extr...
6 篇 natural language...
5 篇 graph neural net...
5 篇 graph convolutio...
4 篇 data mining
4 篇 bert
3 篇 cognition
3 篇 transformers
3 篇 multi-hop reason...
3 篇 evidence retriev...
3 篇 evidence extract...
3 篇 attention mechan...
2 篇 pretrained langu...
2 篇 reinforcement le...
2 篇 graph attention ...
2 篇 task analysis
2 篇 multi-head atten...
2 篇 graph attention ...
2 篇 graph neural net...

机构

4 篇 chongqing univ c...
3 篇 soochow univ sch...
3 篇 nanjing univ sci...
3 篇 nanjing univ chi...
2 篇 chongqing univ k...
2 篇 fudan univ sch c...
2 篇 fudan univ sch c...
2 篇 chongqing ind bi...
2 篇 univ queensland ...
2 篇 dalian univ tech...
2 篇 dalian maritime ...
2 篇 hunan normal uni...
2 篇 northeastern uni...
2 篇 suzhou univ sci ...
2 篇 north china univ...
2 篇 beijing jiaotong...
2 篇 hunan normal uni...
2 篇 state key lab ma...
2 篇 shanghai univ sc...
2 篇 chengdu text col...

作者

4 篇 xue zhongxuan
4 篇 dai qizhu
4 篇 zhong jiang
4 篇 li xue
4 篇 li rongzhen
3 篇 zhang kun
3 篇 yuan changsen
3 篇 sun qi
3 篇 liu an
3 篇 li zhixu
3 篇 zhao lei
3 篇 li xun
3 篇 qu jianfeng
3 篇 lin hongfei
3 篇 xu tiancheng
3 篇 huang kun
3 篇 huang heyan
2 篇 fu qiming
2 篇 chen jianping
2 篇 xu jiajie

语言

74 篇 英文

检索条件"主题词=Document-level relation extraction"

共 74 条记录，以下是41-50 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Evidence-aware document-level relation extraction 22

Evidence-aware Document-level Relation Extraction

引用

31st ACM International Conference on Information and Knowledge Management (CIKM)

作者： Xu, Tianyu Hua, Wen Qu, Jianfeng Li, Zhixu Xu, Jiajie Liu, An Zhao, Lei Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Univ Queensland Sch Informat Technol & Elect Engn St Lucia Qld Australia Fudan Univ Sch Comp Sci Shanghai Key Lab Data Sci Shanghai Peoples R China

ISBN: (纸本)9781450392365

document-level relation extraction (RE) is a promising task aiming at identifying relations of multiple entity pairs in a document. However, in most cases, a relational fact can be expressed enough via a small subset of sentences from the document, namely evidence sentence. Moreover, there often exist strong semantic correlations between evidence sentences that collaborate together to describe a specific relation. To address these challenges, we propose a novel evidence-aware model for document-level RE. Particularly, we formulate evidence sentence selection as a sequential decision problem through a crafted reinforcement learning mechanism. Considering the explosive search space of our agent, an efficient path searching strategy is executed on the converted document graph to heuristically obtain hopeful sentences and feed them to reinforcement learning. Finally, each entity pair owns a customized-filtered document for further inferring the relation between them. We conduct various experiments on two document-level RE benchmarks and achieve a remarkable improvement over previous competitive baselines, verifying the effectiveness of our ***-level relation extraction (RE) is a promising task aiming at identifying relations of multiple entity pairs in a document. However, in most cases, a relational fact can be expressed enough via a small subset of sentences from the document, namely evidence sentence. Moreover, there often exist strong semantic correlations between evidence sentences that collaborate together to describe a specific relation. To address these challenges, we propose a novel evidence-aware model for document-level RE. Particularly, we formulate evidence sentence selection as a sequential decision problem through a crafted reinforcement learning mechanism. Considering the explosive search space of our agent, an efficient path searching strategy is executed on the converted document graph to heuristically obtain hopeful sentences and feed them

关键词： document-level relation extraction reinforcement learning evidence extractiondocument-level relation extraction reinforcement learning evidence extraction

来源：评论

学校读者我要写书评

暂无评论

Improving document-level relation extraction via Contextualizing Mention Representations and Weighting Mention Pairs 11

Improving Document-level Relation Extraction via Contextuali...

引用

11th IEEE International Conference on Knowledge Graph (IEEE ICKG)

作者： Jiang, Ping Mao, Xian-Ling Bian, Binbin Huang, Heyan Beijing Inst Technol Sch Comp Sci Beijing Peoples R China

ISBN: (纸本)9781728181561

document-level relation extraction (RE) has attracted considerable attention, because a large number of relational facts are expressed in multiple sentences. Recently, encoder-aggregator based models have become promising for document-level RE. However, these models have two shortcomings: (i) they cannot obtain contextualized representations of a mention by low computational cost, when the mention is involved in different entity pairs;(ii) they ignore the different weights for the mention pairs of a target entity pair. To tackle the above two problems, in this paper, we propose a novel encoder-attender-aggregator model, which introduces two attenders between the encoder and aggregator. Specifically, a mutual attender is first employed on the selected head and tail mentions to efficiently produce contextualized mention representations. Then, an integration attender is utilized to weight the mention pairs of a target entity pair. Extensive experiments on two document-level RE datasets show that the proposed model performs better than the state-of-the-art baselines. Our codes are publicly available at "https://***/nefujiangping/EncAttAgg".

关键词： relation extraction document-level relation extraction Multihead attention

来源：评论

学校读者我要写书评

暂无评论

Multi-relation Identification for Few-Shot document-level relation extraction 1

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Wang, Dazhuang Wu, Shaojuan Zhang, Xiaowang Feng, Zhiyong Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China

ISBN: (数字)9783031442018

ISBN: (纸本)9783031442001;9783031442018

document-level relation extraction aims to extract relations between entities mentioned in the given text. Existing approaches characterize relations by concatenating the representation of entities from numerous instances for each relation. However, it fails to identify multiple relations that may be expressed by the same entity pair in few-shot scenarios, since there may be only one instance for some relations. In this paper, we propose a Context-aware Hybrid Attention Network (CHAN) for few-shot document-level relation extraction to identify multi-relation. Specifically, we design instance-specific attention to localize the relevant context for each entity pair and capture keywords associated with different relations. In addition, we introduce a contrastive prototypical network to further distinguish the subtle difference between multiple relations. Experimental results show that CHAN achieved the best performance compared to previous methods, especially the F1 of the multi-relation identification is improved by 17.94% under 1-doc setting in FREDo benchmark.

关键词： few-shot learning document-level relation extraction multi-relation context-aware mechanism

来源：评论

学校读者我要写书评

暂无评论

Understanding More Knowledge Makes the Transformer Perform Better in document-level relation extraction 15

Understanding More Knowledge Makes the Transformer Perform B...

引用

15th Asian Conference on Machine Learning (ACML)

作者： Chen, Haotian Chen, Yijiang Zhou, Xiangdong Fudan Univ Sch Comp Sci Shanghai Peoples R China

relation extraction plays a vital role in knowledge graph construction. In contrast with the traditional relation extraction on a single sentence, extracting relations from multiple sentences as a whole will harvest more valuable and richer knowledge. Recently, the Transformer-based pre-trained language models (TPLMs) are widely adopted to tackle document-level relation extraction (DocRE). Graph-based methods, aiming to acquire knowledge between entities to form entity-level relation graphs, have facilitated the rapid development of DocRE by infusing their proposed models with the knowledge. However, beyond entity-level knowledge, we discover many other kinds of knowledge that can aid humans to extract relations. It remains unclear whether and in which way they can be adopted to improve the performance of the Transformer, which affects the maximum performance gain of Transformer-based methods. In this paper, we propose a novel weighted multi-channel Transformer (WMCT) to infuse unlimited kinds of knowledge into the vanilla Transformer. Based on WMCT, we also explore five kinds of knowledge to enhance both its reasoning ability and expressive power. Our extensive experimental results demonstrate that: (1) more knowledge makes the performance of the Transformer better and (2) more informative knowledge leads to more performance gain. We appeal to future Transformer-based work to consider exploring more informative knowledge to improve the performance of the Transformer.

关键词： document-level relation extraction graph-based method a weighted multi-channel Transformer

来源：评论

学校读者我要写书评

暂无评论

Infusing Dependency Syntax Information into a Transformer Model for document-level relation extraction from Biomedical Literature 8th

Infusing Dependency Syntax Information into a Transformer Mo...

引用

8th Annual China Conference on Health Information Processing (CHIP)

作者： Yang, Ming Zhang, Yijia Liu, Da Du, Wei Di, Yide Lin, Hongfei Dalian Maritime Univ Sch Informat Sci & Technol Dalian 116024 Liaoning Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian 116023 Lioaoning Peoples R China

ISBN: (纸本)9789811998645;9789811998652

In biomedical domain, document-level relation extraction is a challenging task that offers a new and more effective approach for long and complex text mining. Studies have shown that the Transformer models the dependencies of any two tokens without regard to their syntax-level dependency in the sequence. In this work, we propose a Dependency Syntax Transformer Model, i.e., the DSTM model, to improve the Transformer's ability in long-range modeling dependencies. Three methods are proposed for introducing dependency syntax information into the Transformer to enhance the attention of tokens with dependencies in a sentence. The dependency syntax Transformer model improves the Transformer's ability to handle long text in document-level relation extraction. Our experimental results on the document-level relation extraction dataset CDR in the biomedical field prove the validity of the DSTM model, and the experimental results on the generic domain dataset DocRED prove the universality.

关键词： document-level relation extraction Dependency syntax information Transformer model Attention mechanism Biomedical literature

来源：评论

学校读者我要写书评

暂无评论

Refining ChatGPT for document-level relation extraction: A Multi-dimensional Prompting Approach 20th

Refining ChatGPT for Document-Level Relation Extraction: A M...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Zhu, Weiran Wang, Xinzhi Chen, Xue Luo, Xiangfeng Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China

ISBN: (纸本)9789819756681;9789819756698

This work explores the efficacy of large language models (LLMs) like ChatGPT and GPT-4 in document-level relation extraction (DocRE). Our work begins with the assessment of the zero-shot capabilities of leading LLMs in DocRE, followed by an in-depth exploration of ChatGPT's performance through fine-tuning. We introduce Multi-Dimensional-Prompting, a prompting framework inspired by existing symbolic and arithmetic reasoning techniques in LLMs. Our methodology includes: (1) a task decomposition strategy that breaks down DocRE into sequential sub-tasks of entity pair extraction and relation classification;(2) a process decomposition strategy to refine the DocRE logic, enhancing prompts for more efficient processing;and (3) a relation-type decomposition strategy, classifying predefined relation types into categories, each can be processed by specialized models for a comprehensive final outcome. Our methods improve performance on benchmark datasets DocRED and Re-DocRED, with our fine-tuned ChatGPT outperforming current state-of-the-art methods.

关键词： document-level relation extraction ChatGPT Prompt Engineering

来源：评论

学校读者我要写书评

暂无评论

Pre-classification Supporting Reasoning for document-level relation extraction 10

Pre-classification Supporting Reasoning for Document-level R...

引用

10th International Joint Conference on Knowledge Graphs (IJCKG)

作者： Zhao, Jiehao Duan, Guiduo Huang, Tianxi Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Trusted Cloud Comp & Big Data Key Lab Sichuan Pro Chengdu Peoples R China Chengdu Text Coll Dept Fundamental Courses Chengdu Peoples R China

ISBN: (纸本)9781450395656

The document-level relation extraction task aims to extract relational triples from a document consisting of multiple sentences. Most previous models focus on modeling the dependency between the entities and neglect the reasoning mechanism. Some other models construct paths implicitly between co-sentence entities to find semantic relations. However, they ignore that there are interactions between different triples, especially some triples play an import role in predicting others. In this short research paper, we propose a new two stage framework PCSR(Pre-classification Supporting Reasoning) which captures the interactions between triples and utilizes these information for reasoning. Specifically, we make a pre-classification for each entity pair in the first stage. Then we aggregate the embeddings of predicted triples to enhance entity representation and make a new classification. Since the second classification could find triples missed in the first stage, we take the result as the supplement of the prior one. Experiments on DocRED show that our method achieves an F1 score of 62.11. Compared with the previous state-of-the-art model, our model increase by 0.81 on the test set, which demonstrates the effectiveness of our reasoning mechanism.

关键词： Information extraction document-level relation extraction BERT Reasoning Mechanism

来源：评论

学校读者我要写书评

暂无评论

NN-Denoising: A Low-Noise Distantly Supervised document-level relation extraction Scheme Using Natural Language Inference and Negative Sampling 32nd

NN-Denoising: A Low-Noise Distantly Supervised Document-Leve...

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Pan, Mengting Wang, Ye Chen, Zhiyun East China Normal Univ Shanghai 200000 Peoples R China

ISBN: (纸本)9783031442124;9783031442131

The task of document-level relation extraction (DocRE) is crucial in the field of natural language processing, as it aims to extract semantic relations between entities in a given document to facilitate deeper comprehension. Previous methods have primarily focused on fully supervised learning for DocRE, which requires a large amount of human-annotated training data, making it a tedious and laborious task. Recently, more and more attention has been paid to the incomplete labeling problem in human-annotated data, and it is believed to be the bottleneck of model performance. To address this limitation and mitigate annotation costs, we propose a low-noise distant supervision scheme for DocRE, called NN-Denoising, that combines natural language inference (NLI) models and negative sampling to filter out noise in the training data. The NLI model serves as a pre-filter for denoising the distant supervision (DS) labels, while negative sampling is employed to overcome the false negative problem in the filtered data. Our experimental results on a large-scale DocRE benchmark demonstrate the superiority of the proposed approach over existing baselines in distant supervision learning. Specifically, NN-Denoising achieves an improvement of 15.83 F1 points and 10.34 F1 points compared to the ATLOP and SSR-PU models, respectively.

关键词： document-level relation extraction Distantly Supervised Learning Low-Noise

来源：评论

学校读者我要写书评

暂无评论

NA-Aware Machine Reading Comprehension for document-level relation extraction 1

引用

21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Zhang, Zhenyu Yu, Bowen Shu, Xiaobo Liu, Tingwen Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (数字)9783030865238

ISBN: (纸本)9783030865238;9783030865221

document-level relation extraction aims to identify semantic relations between target entities from the *** of the existing work roughly treats the document as a long sequence and produces target-agnostic representation for relation prediction, limiting the model's ability to focus on the relevant context of target entities. In this paper, we reformulate the document-level relation extraction task and propose a NA-aware machine Reading Comprehension (NARC) model to tackle this problem. Specifically, the input sequence formulated as the concatenation of a head entity and a document is fed into the encoder to obtain comprehensive target-aware representations for each entity. In this way, the relation extraction task is converted into a reading comprehension problem by taking all the tail entities as candidate answers. Then, we add an artificial answer NO-ANSWER (NA) for each query and dynamically generate a NA score based on the decomposition and composition of all candidate tail entity features, which finally weighs the prediction results to alleviate the negative effect of having too many no-answer instances after task reformulation. Experimental results on DocRED with extensive analysis demonstrate the effectiveness of NARC.

关键词： document-level relation extraction Machine reading comprehension No-answer query

来源：评论

学校读者我要写书评

暂无评论

CRFLOE: Context Region Filter and relation Word Aware for document-level relation extraction 20th

CRFLOE: Context Region Filter and Relation Word Aware for Do...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Yang, DanPing Li, XianXian Wu, Hao Zhou, Aoxiang Liu, Peng Guangxi Normal Univ Sch Comp Sci & Engn Guilin 541004 Peoples R China Guangxi Normal Univ Minist Educ Key Lab Educ Blockchain & Intelligent Technol Guilin 541004 Peoples R China

ISBN: (纸本)9789819756681;9789819756698

The goal of document-level relation extraction (DocRE) is to identify all entity pair relations from a document in one pass. One challenge faced by DocRE is mining the decisive context of entity pair relations from the document. Nevertheless, it is noteworthy that even among human-annotated key sentences, only a limited subset can effectively function as pivotal contextual information. To enhance the acquisition and utilization of crucial contextual information, we propose a pioneering framework namedCRFLOE(ContextRegion Filter and relation Word Aware). This framework operates by segmenting the context with a focus on entities, subsequently computing region-level attention scores, and filtering out contextual information with low scores at a coarse-grained level. Following this filtration, fine-grained score adjustment is conducted on the remaining candidate regions. Furthermore, we introduce additional prior knowledge of relation word to calibrate the final relation scores, further improving the performance of our model. We conducted experiments on four DocRE datasets: DocRED and ReDocRED, which are two recently released large-scale datasets, as well as GDA and CDR in the biomedical field. Our findings demonstrate the effectiveness of CRFLOE.

关键词： document-level relation extraction Pretrained Language Models Context Region Filter relation Word

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共8页 << < 1 2 3 4 5 6 7 8 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：