III: Small: EAGER: Representation Learning of Connotation and Denotation Knowledge for Atomic Information Units
III:小:EAGER:原子信息单元的内涵和外延知识的表示学习
基本信息
- 批准号:1914489
- 负责人:
- 金额:$ 8万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2019
- 资助国家:美国
- 起止时间:2019-07-01 至 2022-06-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Many complex large-scale symbolic systems have been developed by human society, such as natural languages, logic, mathematics, which can encode very complicated information. While the major application and motivation for symbolic systems is communication among different entities either horizontally/spatially (e.g., a speaker gives a presentation in a meeting) and/or vertically/temporarily (e.g., reading a history book), information represented by these symbolic systems are ultimately created, revised, and processed/computed by human brain, a large volume of neural network processing information at the sub-symbolic level. What is the relationship and connection between symbolic processing and sub-symbolic processing? What is the internal structure and mechanism at the sub-symbolic level that supports symbol-level processing? Is there any deep computation mechanism for symbolic systems beyond shallow techniques (e.g., string match in Natural Language Processing)? All of these questions are fundamental to multiple research fields and scientific disciplines, and have attracted researchers and scientists of many generations ranging from the early study of denotation and connotation in philosophy to more recent investigation of semantic space construction. This project will focus on modeling and representation of denotation information for words in a natural language. With the fundamental focus on understanding of semantics at the sub-symbolic level, this project will provide valuable insight to natural languages and human intelligence in general, pave the way to build a large-scale testbed for fields such as computational linguistics, psychology, language acquisition, and bring broad interdisciplinary impact on many scientific fields. This project includes a carefully-crafted education component, which directly promotes undergraduate and graduate research and training, encourages minority and woman participation, and has a sustainable impact on Computer Science curricula and courseware beyond the scope of this project.The overall goal of this project is to investigate how to represent a word with an internal structure (e.g., a neural network) beyond the existing approach of vector space to support more sophisticated symbolic processing techniques beyond shallow string matching. Specifically, there are three research objectives in this project. The first objective is to study the various options for representing internal structures of a word, which is closely related to the active research field of Neural Architecture Search. In the second objective, due to the large vocabulary size in a natural language and complex connotation information for modeling, a huge number of parameters in these neural architectures need to be learned and tuned, a bootstrapping approach will be developed to overcome the problem of data sparsity that challenges many deep learning models. With an unsupervised approach, the third objective of this project is to investigate a viable way for large-scale knowledge acquisition, which is generally recognized as a serious barrier for building real-world Artificial Intelligence systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
人类社会发展出了许多复杂的大规模符号系统,如自然语言、逻辑、数学等,它们可以对非常复杂的信息进行编码。虽然符号系统的主要应用和动机是不同实体之间的水平/空间通信(例如,发言者在会议中给出演示)和/或垂直地/临时地(例如,阅读历史书),这些符号系统所代表的信息最终由人脑创建、修改和处理/计算,人脑是在亚符号水平上处理信息的大量神经网络。符号加工和次符号加工之间的关系和联系是什么?支持符号级处理的子符号级的内部结构和机制是什么?符号系统是否有超越浅层技术的深层计算机制(例如,自然语言处理中的字符串匹配)?所有这些问题都是多个研究领域和科学学科的基础,并吸引了许多代的研究人员和科学家,从哲学中的外延和内涵的早期研究到最近的语义空间构建研究。这个项目将集中在自然语言中单词的指称信息的建模和表示。该项目的基本重点是在子符号层面理解语义,将为自然语言和人类智能提供有价值的见解,为计算语言学,心理学,语言习得等领域建立大规模测试平台铺平道路,并对许多科学领域产生广泛的跨学科影响。该项目包括一个精心设计的教育部分,直接促进本科生和研究生的研究和培训,鼓励少数民族和妇女的参与,并对计算机科学课程和课件产生可持续的影响,超出了该项目的范围。神经网络)以支持超越浅串匹配的更复杂的符号处理技术。具体而言,本项目有三个研究目标。第一个目标是研究用于表示词的内部结构的各种选项,这与神经结构搜索的活跃研究领域密切相关。在第二个目标中,由于自然语言的词汇量很大,建模的内涵信息很复杂,这些神经架构中的大量参数需要学习和调整,将开发一种自举方法来克服挑战许多深度学习模型的数据稀疏问题。该项目的第三个目标是通过无监督的方法,研究大规模知识获取的可行方法,这通常被认为是构建现实世界人工智能系统的严重障碍。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Fall risk assessment through a synergistic multi-source DNN learning model
- DOI:10.1016/j.artmed.2022.102280
- 发表时间:2022-05
- 期刊:
- 影响因子:7.5
- 作者:Olga Andreeva;Wei Ding;Suzanne G. Leveille;Yurun Cai;Ping Chen
- 通讯作者:Olga Andreeva;Wei Ding;Suzanne G. Leveille;Yurun Cai;Ping Chen
Contrastive Learning of Sentence Representations
- DOI:
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Hefei Qiu;Wei Ding;Ping Chen
- 通讯作者:Hefei Qiu;Wei Ding;Ping Chen
{{
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 }}
Ping Chen其他文献
Interactive Visualization of Large High-Dimensional Datasets
大型高维数据集的交互式可视化
- DOI:
- 发表时间:
2009 - 期刊:
- 影响因子:0
- 作者:
Wei Ding;Ping Chen - 通讯作者:
Ping Chen
[Detection of aspiration of nasopharyngeal secretion and the relationship between the aspiration of nasopharyngeal secretion and the incidence of pneumonia].
鼻咽分泌物误吸检测及鼻咽分泌物误吸与肺炎发病的关系[J].
- DOI:
10.3760/cma.j.issn.1001-0939.2015.07.010 - 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Ni Liu;Zeguang Zheng;Ping Chen;P. Hou;Xinni Wang;Hongyi Li;Rongchang Chen - 通讯作者:
Rongchang Chen
Dynamic Magnetic Properties of Electrospun NiZn Spinel Ferrite Nanofibers
电纺镍锌尖晶石铁氧体纳米纤维的动态磁性能
- DOI:
10.1109/tmag.2014.2325711 - 发表时间:
2014 - 期刊:
- 影响因子:2.1
- 作者:
Ping Chen;Ruixin Wu;J. Xiao - 通讯作者:
J. Xiao
α-hydroxyamide derived aminodiols as potent inhibitors of hiv protease
α-羟基酰胺衍生的氨基二醇作为艾滋病毒蛋白酶的有效抑制剂
- DOI:
10.1016/0960-894x(95)00293-3 - 发表时间:
1995 - 期刊:
- 影响因子:0
- 作者:
Saleem Ahmad;A. Ashfaq;M. Alam;G. Bisacchi;Ping Chen;P. Cheng;J. Greytok;M. Hermsmeier;P. Lin;Karen A. Lis;Z. Merchant;Toomas Mitt;M. Skoog;S. Spergel;J. Tino;G. Vite;R. Colonno;R. Zahler;J. Barrish - 通讯作者:
J. Barrish
Suppression of V-pits formation in InGaN layer by stepped growth with annealing interval
通过退火间隔阶梯生长抑制 InGaN 层中 V 坑的形成
- DOI:
10.1016/j.surfin.2021.101691 - 发表时间:
2022-02 - 期刊:
- 影响因子:6.2
- 作者:
Feng Liang;Degang Zhao;Zongshun Liu;Ping Chen;Jing Yang - 通讯作者:
Jing Yang
Ping Chen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('Ping Chen', 18)}}的其他基金
Collaborative Research: EAGER: Deep Learning-based Multimodal Analysis of Sleep
合作研究:EAGER:基于深度学习的睡眠多模态分析
- 批准号:
2334665 - 财政年份:2023
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
III: Small: Collaborative Research: Study of Neural Architectural Components in Physics-Informed Deep Neural Networks for Extreme Flood Prediction
III:小型:协作研究:用于极端洪水预测的物理信息深度神经网络中的神经架构组件研究
- 批准号:
2008202 - 财政年份:2020
- 资助金额:
$ 8万 - 项目类别:
Continuing Grant
Supporting U.S.-Based Students to Participate in the 2018 IEEE International Conference on Data Mining (ICDM 2018)
支持美国学生参加2018年IEEE数据挖掘国际会议(ICDM 2018)
- 批准号:
1836469 - 财政年份:2018
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: Advanced Machine Learning Techniques to Discover Disease Subtypes in Cancer
EAGER:先进的机器学习技术发现癌症疾病亚型
- 批准号:
1743010 - 财政年份:2017
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Project: Enriching Security Curricula and Enhancing Awareness of Security in Computer Science and Beyond
合作项目:丰富安全课程并增强计算机科学及其他领域的安全意识
- 批准号:
1423915 - 财政年份:2014
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Project: Enriching Security Curricula and Enhancing Awareness of Security in Computer Science and Beyond
合作项目:丰富安全课程并增强计算机科学及其他领域的安全意识
- 批准号:
1241661 - 财政年份:2012
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
REU Site: Research Experiences in Algorithm Design and Analysis for Students in Undergraduate Institutions
REU网站:本科院校学生算法设计与分析研究经验
- 批准号:
0851984 - 财政年份:2009
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Research: An Interactive Undergraduate Data Mining Course with Industrial-Strength Projects
协作研究:具有工业强度项目的交互式本科数据挖掘课程
- 批准号:
0737408 - 财政年份:2008
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Research: Module-Based Computer Security Courses and Laboratory for Small and Medium Sized Universities
合作研究:中小型大学基于模块的计算机安全课程和实验室
- 批准号:
0311385 - 财政年份:2003
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
相似国自然基金
昼夜节律性small RNA在血斑形成时间推断中的法医学应用研究
- 批准号:
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
tRNA-derived small RNA上调YBX1/CCL5通路参与硼替佐米诱导慢性疼痛的机制研究
- 批准号:n/a
- 批准年份:2022
- 资助金额:10.0 万元
- 项目类别:省市级项目
Small RNA调控I-F型CRISPR-Cas适应性免疫性的应答及分子机制
- 批准号:32000033
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
Small RNAs调控解淀粉芽胞杆菌FZB42生防功能的机制研究
- 批准号:31972324
- 批准年份:2019
- 资助金额:58.0 万元
- 项目类别:面上项目
变异链球菌small RNAs连接LuxS密度感应与生物膜形成的机制研究
- 批准号:81900988
- 批准年份:2019
- 资助金额:21.0 万元
- 项目类别:青年科学基金项目
肠道细菌关键small RNAs在克罗恩病发生发展中的功能和作用机制
- 批准号:31870821
- 批准年份:2018
- 资助金额:56.0 万元
- 项目类别:面上项目
基于small RNA 测序技术解析鸽分泌鸽乳的分子机制
- 批准号:31802058
- 批准年份:2018
- 资助金额:26.0 万元
- 项目类别:青年科学基金项目
Small RNA介导的DNA甲基化调控的水稻草矮病毒致病机制
- 批准号:31772128
- 批准年份:2017
- 资助金额:60.0 万元
- 项目类别:面上项目
基于small RNA-seq的针灸治疗桥本甲状腺炎的免疫调控机制研究
- 批准号:81704176
- 批准年份:2017
- 资助金额:20.0 万元
- 项目类别:青年科学基金项目
水稻OsSGS3与OsHEN1调控small RNAs合成及其对抗病性的调节
- 批准号:91640114
- 批准年份:2016
- 资助金额:85.0 万元
- 项目类别:重大研究计划
相似海外基金
EAGER: Evaluation and implementation of a newly developed olfactometer for the study of sensory ecology in small marine organisms
EAGER:评估和实施新开发的嗅觉计,用于研究小型海洋生物的感官生态学
- 批准号:
2310259 - 财政年份:2023
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: III: Small: Green Granular Neural Networks with Fast FPGA-based Incremental Transfer Learning
EAGER:III:小型:具有基于 FPGA 的快速增量迁移学习的绿色粒度神经网络
- 批准号:
2234227 - 财政年份:2022
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: Develop Robust Light-Scattering Computational Capability Based on the Method of Separation of Variables in Spheroidal Coordinates for Small-to-Large Spheroids
EAGER:基于从小到大球体的球体坐标中的变量分离方法,开发鲁棒的光散射计算能力
- 批准号:
2153239 - 财政年份:2021
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: SaTC: CORE: Small: Decentralized Data Assurance by Fair Proof of Work Consensus Federated Ledgers
EAGER:SaTC:核心:小型:通过公平工作证明共识联合账本实现去中心化数据保证
- 批准号:
2141468 - 财政年份:2021
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Resarch: EAGER: Mapping small molecules in the root meristem
合作研究:EAGER:绘制根分生组织中的小分子
- 批准号:
2028649 - 财政年份:2020
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Research: EAGER: Mapping small molecules in the root meristem
合作研究:EAGER:绘制根分生组织中的小分子
- 批准号:
2028776 - 财政年份:2020
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: SaTC: CORE: Small: Blockchain Architectures for Resource-Constrained Devices
EAGER:SaTC:核心:小型:资源受限设备的区块链架构
- 批准号:
1937357 - 财政年份:2019
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: Imaging of Element-Specific 3D Distribution Dynamics in Working Bimetallic Catalysts by in situ Anomalous Small-Angle X-Ray Scattering
EAGER:通过原位反常小角 X 射线散射对工作双金属催化剂中元素特定的 3D 分布动力学进行成像
- 批准号:
1838277 - 财政年份:2018
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
EAGER: Small Motionless Antenna with Reconfigurable Transmission
EAGER:具有可重新配置传输功能的小型静止天线
- 批准号:
1832860 - 财政年份:2018
- 资助金额:
$ 8万 - 项目类别:
Standard Grant
Collaborative Research: DCL: HBCU EAGER Network effects, competition and survival of small and minority owned firms in public procurement
合作研究:DCL:HBCU EAGER 公共采购中小型和少数族裔企业的网络效应、竞争和生存
- 批准号:
1745604 - 财政年份:2017
- 资助金额:
$ 8万 - 项目类别:
Standard Grant