This Project Grant award from the National Science Foundation (NSF) Division of Information and Intelligent Systems under the Computer and Information Science and Engineering program (CFDA 47.070) provides $499,948 to Iowa State University of Science and Technology to develop an adaptable and flexible information extraction framework. The goal is to enable automated extraction of structured information from unstructured scientific literature without relying on costly expert annotations. The...
This Project Grant award from the National Science Foundation (NSF) under the Integrative Activities program (CFDA 47.083) will support the development of novel deep generative models and algorithms for analyzing and visualizing scientific texts. The $224,036 award to New Mexico State University (NMSU) will fund a fellowship for an assistant professor and graduate student training. The project aims to create algorithms that model the intent, topics, and embeddings within scientific documents, as...
This $550,000 award from the National Science Foundation's (NSF) Technology, Innovation, and Partnerships (CFDA 47.084) program supports the development of a hybrid, scalable data management system to improve access to scientific knowledge in data science. The project aims to create an intelligent, user-friendly interface that can extract, organize, and provide deep access to relevant concepts from peer-reviewed scientific literature. Key objectives include: Building a comprehensive knowledge...
This $220,000 Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program aims to empower AI researchers to more easily search, discover, and use AI-ready data sets. The goal is to streamline and democratize AI research by developing data discovery services that leverage AI techniques to automatically extract and store data citation information from research publications. These discovery services will be integrated into the...
This Project Grant from the National Science Foundation's Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $1,167,492 to Carnegie Mellon University to support research into expert-in-the-loop neural summarization for specialized domains from July 2022 to June 2026. Specifically, the university will critically evaluate and extend the capabilities of modern pre-trained neural summarization models for use...
The National Science Foundation has awarded a $299,990 Project Grant to Columbia University to develop a prototype system using large language models to assist in the review process for releasing government records. The project aims to determine the additional data and training required to achieve acceptable levels of accuracy in using large language models to identify information that is already in the public domain, in order to streamline the document review process. The iterative system...
This National Science Foundation (NSF) Project Grant award under the Mathematical and Physical Sciences program (CFDA 47.049) supports a project at the University of Utah focused on using advanced natural language processing and large language models to automatically extract materials data from scientific literature. The $200,000 award, made on an EAGER proposal, aims to tackle the challenge of materials data being locked in unstructured PDF formats that are difficult to utilize in modern...
This $300,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports the development of a structure-guided reasoning approach for multi-hop, complex reasoning using large language models (LLMs). The project aims to create a framework integrating three key tasks: retrieving task-focused data and information, structuring the retrieved data and knowledge, and reasoning on the structured data and knowledge. It will...
The National Science Foundation awarded $1,200,000 under the Computer and Information Science and Engineering program (CFDA 47.070) to Northeastern University for a four-year project grant beginning July 2022. The grant supports research to advance neural summarization models for specialized domains with limited training data, where factually accurate summaries are critical. Researchers will evaluate state-of-the-art models fine-tuned for domains like medicine and characterize their factual...
This Project Grant award, valued at $347,549, was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) federal grant program. The award supports research by New York University (NYU) to develop interactive language systems that can critically reason about textual sources to provide high-quality, up-to-date information. The key focus areas include: (1) expanding the definition of document relevancy to incorporate...