III: Small: Collaborative Research: Global Event and Trend Archive Research (GETAR)

III：小型：协作研究：全球事件和趋势档案研究 (GETAR)

• 批准号: 1619028
• 负责人: Edward Fox
• 金额: $ 44.6万
• 依托单位: Virginia Polytechnic Institute and State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1619028&HistoricalAwards=false
• 关键词: III; Small; Collaborative; Research; Global

This project will devise interactive, integrated, digital library/archive systems coupled with linked and expert-curated webpage/tweet collections, covering key parts of the 1997-2020 timeframe, supporting research on urgent global challenge events and initiatives. It will allow diverse stakeholder communities to interactively collect, organize, browse, visualize, study, analyze, summarize, and explore content and sources related to biodiversity, climate change, crises, disasters, elections, energy policy, environmental policy/planning, geospatial information, green engineering, human rights, inequality, migrations, nuclear power, population growth, resiliency, shootings, sustainability, violence, etc. Studying and addressing important global issues, by scholars, the public, and K-12 students, will be enhanced through tailored interfaces coupled with important collections that will be primary resources for understanding the modern world and its challenges, as well as initiatives, trends, and solutions.Research will extend work on modeling trends, events, and sources, to guide focused crawling, information extraction, tagging, and collaboration. Domain experts will leverage rich event models, exploiting the generality of the 5S framework (Societies, Scenarios, Spaces, Structure, Streams), extending from word, n-gram, topic, concept, and language models. This research will enable efficient assembly of knowledge bases, rapid prototyping of interfaces, gathering/curation of collections with high precision and recall, and flexible discovery in support of research and learning. Interdisciplinary research advances will address digital humanities, web archiving, information retrieval, natural language processing, machine learning, and the construction of valuable interactive/collaborative interfaces. For further information see the project web site at eventsarchive.org.

该项目将设计交互式、综合性数字图书馆/档案系统，加上链接和专家策划的网页/推特收藏，涵盖1997-2020年时间框架的关键部分，支持对紧迫的全球挑战事件和倡议的研究。它将允许不同的利益相关者社区以交互方式收集，组织，浏览，可视化，研究，分析，总结和探索与生物多样性，气候变化，危机，灾害，选举，能源政策，环境政策/规划，地理空间信息，绿色工程，人权，不平等，移民，核电，人口增长，弹性，枪击，可持续性，暴力，研究和解决重要的全球性问题，学者，公众和K-12学生，将通过定制的界面加上重要的集合，将是理解现代世界及其挑战的主要资源，以及倡议，趋势和解决方案得到加强。研究将扩展建模趋势，事件和来源的工作，以指导重点抓取，信息提取，标签和协作。领域专家将利用丰富的事件模型，利用5S框架（社会，场景，空间，结构，流）的通用性，从单词，n-gram，主题，概念和语言模型扩展。这项研究将使知识库的有效组装，界面的快速原型，收集/高精度和召回率的集合策展，以及支持研究和学习的灵活发现。跨学科的研究进展将解决数字人文，网络存档，信息检索，自然语言处理，机器学习，以及有价值的交互/协作界面的建设。欲了解更多信息，请访问项目网站eventsarchive.org。

项目成果

LATTE: Latent Type Modeling for Biomedical Entity Linking

• DOI: 10.1609/aaai.v34i05.6526
• 发表时间: 2019-11
• 期刊: ArXiv
• 作者: Ming Zhu;B. Celikkaya;Parminder Bhatia;Chandan K. Reddy

Predicting interval time for reciprocal link creation using survival analysis

• DOI: 10.1007/s13278-018-0494-1
• 发表时间: 2018-03
• 期刊: Social Network Analysis and Mining
• 影响因子: 2.8
• 作者: Vachik S. Dave;M. Hasan;Baichuan Zhang;Chandan K. Reddy

Pre-Processing Censored Survival Data Using Inverse Covariance Matrix Based Calibration

使用基于逆协方差矩阵的校准来预处理删失生存数据

• DOI: 10.1109/tkde.2017.2719028
• 发表时间: 2017
• 期刊: IEEE Transactions on Knowledge and Data Engineering
• 影响因子: 8.9
• 作者: Vinzamuri, Bhanukiran;Li, Yan;Reddy, Chandan K.
• 通讯作者: Reddy, Chandan K.

Adversarial Factorization Autoencoder for Look-alike Modeling

• DOI: 10.1145/3357384.3357807
• 发表时间: 2019-11
• 期刊: Proceedings of the 28th ACM International Conference on Information and Knowledge Management
• 作者: Khoa D. Doan;Pranjul Yadav;Chandan K. Reddy

A Sparse Topic Model for Extracting Aspect-Specific Summaries from Online Reviews

• DOI: 10.1145/3178876.3186069
• 发表时间: 2018-04
• 期刊: Proceedings of the 2018 World Wide Web Conference
• 作者: Vineeth Rakesh;Weicong Ding;Aman Ahuja;Nikhil S. Rao;Yifan Sun;Chandan K. Reddy