III: Medium: Collaborative Research: StructNet: Constructing and Mining Structure-Rich Information Networks for Scientific Research

III：媒介：协作研究：StructNet：为科学研究构建和挖掘结构丰富的信息网络

• 批准号: 2034562
• 负责人: Heng Ji
• 金额: $ 38.81万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-16 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2034562&HistoricalAwards=false
• 关键词: III; Medium; Collaborative; Research; StructNet

Science disciplines have been generating huge volume of research publications, which is of tremendous value but far beyond researchers' capacity to digest and analyze. There is a critical need to automatically (with the help of widely available, general knowledge-bases) transform research text into structured information networks on which advanced search and analytics tools can be developed to facilitate researchers and practitioners to quickly locate knowledge, make inferences, and even generate new scientific hypothesis.This project aims at developing a new data-to-network-to-knowledge (D2N2K) paradigm to transform massive, unstructured but interconnected research text data into actionable knowledge, by integrating semi-structured and unstructured data. First, organized heterogeneous information networks (hence called StructNet) are constructed, and then powerful mining mechanisms on such organized networks are developed. With a focus on biomedical sciences, the project investigates the principles, methodologies and algorithms for (i) construction of relatively structured heterogeneous information networks (called MediNet) by mining biomedical research corpora via attribute extraction, relation typing, and claim mining, and (ii) exploration and mining of the networks so constructed via graph OLAP and task-guided embedding. The project develops an extensible framework to facilitate literature-based scientific research. The study on construction and exploration of MediNet not only impacts biomedical research but also consolidates this data-to-network-to knowledge methodology, readily to be transferred to other domains, for automatic transformation of massive unstructured text data in those domains into structured and actionable knowledge.

科学学科产生了大量的研究出版物，这些出版物具有巨大的价值，但远远超出了研究人员的消化和分析能力。迫切需要将研究文本自动(借助于广泛可用的通用知识库)转换为结构化信息网络，在该网络上可以开发高级搜索和分析工具，以帮助研究人员和从业者快速定位知识、做出推理，甚至生成新的科学假设。该项目旨在开发一种新的数据到网络到知识(D2N2K)范式，通过整合半结构化和非结构化数据，将海量、非结构化但相互关联的研究文本数据转换为可操作的知识。首先构建了有组织的异质信息网络(StructNet)，然后在这种有组织的网络上开发了强大的挖掘机制。该项目以生物医学科学为重点，研究用于(I)通过属性提取、关系分类和索赔挖掘挖掘生物医学研究语料库来构建相对结构化的异质信息网络(称为Medeeet)的原理、方法和算法，以及(Ii)通过图OLAP和任务引导嵌入来探索和挖掘如此构建的网络。该项目开发了一个可扩展的框架，以促进基于文献的科学研究。MEDINET的构建和探索研究不仅影响了生物医学研究，而且巩固了这种数据到网络到知识的方法论，便于转移到其他领域，将这些领域中的海量非结构化文本数据自动转换为结构化和可操作的知识。

项目成果

BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks

• DOI: 10.18653/v1/2021.findings-emnlp.140
• 发表时间: 2021-09
• 作者: T. Lai;Heng Ji;ChengXiang Zhai

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation

• DOI: 10.18653/v1/2021.naacl-demos.8
• 发表时间: 2020-07
• 期刊: ArXiv
• 作者: Qingyun Wang;Manling Li;Xuan Wang;Nikolaus Nova Parulian;G. Han;Jiawei Ma;Jingxuan Tu;Ying Lin;H. Zhang;Weili Liu;Aabhas Chauhan;Yingjun Guan;Bangzheng Li;Ruisong Li;Xiangchen Song;Heng Ji;Jiawei Han;Shih-Fu Chang;J. Pustejovsky;D. Liem;Ahmed Elsayed;Martha Palmer;Jasmine Rah;Cynthia Schneider;Boyan A. Onyshkevych

Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation

• DOI: 10.1109/bibm52615.2021.9669360
• 发表时间: 2021-08
• 期刊: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
• 作者: Chenkai Sun;Weijian Li;Jinfeng Xiao;N. Parulian;ChengXiang Zhai;Heng Ji

Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference

• DOI: 10.18653/v1/2021.acl-long.488
• 发表时间: 2021-05
• 作者: T. Lai;Heng Ji;ChengXiang Zhai;Quan Hung Tran

Chemical-Reaction-Aware Molecule Representation Learning

• 发表时间: 2021-09
• 期刊: ArXiv
• 作者: Hongwei Wang;Weijian Li;Xiaomeng Jin;Kyunghyun Cho;Heng Ji;Jiawei Han;M. Burke