Temporal Knowledge Graph Construction from Text
从文本构建时态知识图
基本信息
- 批准号:21K17816
- 负责人:
- 金额:$ 2.25万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for Early-Career Scientists
- 财政年份:2021
- 资助国家:日本
- 起止时间:2021-04-01 至 2024-03-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
This research aims to build a temporal knowledge graph from the text. In this fiscal year, we constructed FinKG, the temporal knowledge graph in the financial domain using information reported from SEC and market exchange. The temporal information including the report detail and stock price, is extracted using our financial ontology as a template. The temporal information is encoded at the edge of the knowledge graph. Overall, FinKG contained more than 30 million facts. Furthermore, we demonstrate the usefulness of FinKG with two applications: knowledge retrieval and stock price prediction. Knowledge retrieval reveals the complex connection among entities, while aggregated features from FinKG help neural models to better forecast stock prices.
本研究的目的是从文本中构建时间知识图谱。在本财年,我们使用SEC和市场交易所报告的信息构建了金融领域的时间知识图FinKG。使用我们的金融本体作为模板,提取了包括报告详细信息和股票价格在内的时间信息。时间信息在知识图的边缘被编码。总体而言,FinKG包含了3000多万个事实。此外,我们还通过两个应用:知识检索和股票价格预测,证明了FinKG的有效性。知识检索揭示了实体之间的复杂联系,而FinKG的聚合特征有助于神经模型更好地预测股价。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
FinKG: A Core Financial Knowledge Graph for Financial Analysis
- DOI:10.1109/icsc56153.2023.00020
- 发表时间:2023-02
- 期刊:
- 影响因子:0
- 作者:Natthawut Kertkeidkachorn;Rungsiman Nararatwong;Ziwei Xu;R. Ichise
- 通讯作者:Natthawut Kertkeidkachorn;Rungsiman Nararatwong;Ziwei Xu;R. Ichise
Competent Triple Identification for Knowledge Graph Completion under the Open-World Assumption
开放世界假设下知识图补全的胜任三重识别
- DOI:10.1587/transinf.2021edp7148
- 发表时间:2022
- 期刊:
- 影响因子:0.7
- 作者:FARJANA Esrat;KERTKEIDKACHORN Natthawut;ICHISE Ryutaro
- 通讯作者:ICHISE Ryutaro
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
K. Natthawut其他文献
K. Natthawut的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('K. Natthawut', 18)}}的其他基金
Toward Trustworthy Generative AI by Integrating Large Language Model with Knowledge Graph
通过将大型语言模型与知识图相结合,迈向可信赖的生成式人工智能
- 批准号:
24K20834 - 财政年份:2024
- 资助金额:
$ 2.25万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
相似海外基金
CAREER: Towards Open World Event Knowledge Extraction with Weak Supervision
职业:在弱监督下实现开放世界事件知识提取
- 批准号:
2238940 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Continuing Grant
Research on clinical knowledge extraction infrastructure using real-world data derived from electronic medical records
使用电子病历中的真实数据提取临床知识基础设施的研究
- 批准号:
23K17001 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Collaborative Research: CISE-MSI: DP: IIS: Event Detection and Knowledge Extraction via Learning and Causality Analysis for Resilience Emergency Response
协作研究:CISE-MSI:DP:IIS:通过学习和因果关系分析进行事件检测和知识提取,以实现弹性应急响应
- 批准号:
2219615 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Standard Grant
CAREER: Knowledge Extraction and Discovery from Massive Text Corpora via Extremely Weak Supervision
职业:通过极弱监督从海量文本语料库中提取和发现知识
- 批准号:
2239440 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Continuing Grant
Collaborative Research: CISE-MSI: DP: IIS: Event Detection and Knowledge Extraction via Learning and Causality Analysis for Resilience Emergency Response
协作研究:CISE-MSI:DP:IIS:通过学习和因果关系分析进行事件检测和知识提取,以实现弹性应急响应
- 批准号:
2219614 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Standard Grant
A new approach for traffic data management and modeling that combines storage efficiency and immediate knowledge extraction
一种结合存储效率和即时知识提取的交通数据管理和建模新方法
- 批准号:
23K17800 - 财政年份:2023
- 资助金额:
$ 2.25万 - 项目类别:
Grant-in-Aid for Challenging Research (Exploratory)
A real-time system for data streaming and knowledge extraction on mobile devices
移动设备上的数据流和知识提取的实时系统
- 批准号:
DDG-2019-05756 - 财政年份:2021
- 资助金额:
$ 2.25万 - 项目类别:
Discovery Development Grant
Accelerating medicine development timelines through new approaches in knowledge extraction from diverse biological data sets
通过从不同生物数据集中提取知识的新方法加快药物开发进程
- 批准号:
MR/W003996/1 - 财政年份:2021
- 资助金额:
$ 2.25万 - 项目类别:
Research Grant
Revamping Real Estate investments with a Neural Network pipeline for image recognition and knowledge extraction from floor plans and planning applications
使用神经网络管道改造房地产投资,以进行图像识别并从平面图和规划应用程序中提取知识
- 批准号:
10004707 - 财政年份:2021
- 资助金额:
$ 2.25万 - 项目类别:
Collaborative R&D
Knowledge Extraction via Learning Processes and Data Models with Imprecision
通过不精确的学习过程和数据模型提取知识
- 批准号:
RGPIN-2017-06245 - 财政年份:2021
- 资助金额:
$ 2.25万 - 项目类别:
Discovery Grants Program - Individual