This $339,927 federal Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support Georgetown University's development of an intelligent conversational agent. The agent will be built on a hierarchical model-based deep reinforcement learning framework to enable proactive, two-way conversations that can dynamically detect opportunities to expand knowledge and explore new topics. The project...
This five-year 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 $676,344 to the University of Massachusetts for research advancing conversational information retrieval. Specifically, the awardee will develop theoretical foundations and machine learning models for mixed-initiative interactions in information-seeking conversations that go beyond...
This $550,000 Project Grant award from the National Science Foundation (NSF) under the Technology, Innovation, and Partnerships (CFDA 47.084) program supports the development of generative artificial intelligence (AI)-powered products that enable humans to interact and converse with books and other documents. The key products being developed include: Technology to represent the informational content of books and document discussions as a knowledge graph, which will then be used to ground large...
This $175,000 Project Grant award, funded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, supports the development of more reliable and trustworthy question-answering systems that combine large language models with structured knowledge graphs. The research aims to create AI systems that can provide accurate and verifiable responses in critical domains like healthcare and legal services, by integrating the strengths of...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) provides $599,898 to The University of Kentucky Research Foundation to develop advanced, user-centric task-oriented dialog systems. The project aims to enhance the adaptability, flexibility, and personalization of these dialog systems by leveraging large-scale language models and reinforcement learning. Key goals include creating...
This $600,000 Project Grant award, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070), will support research by the University of California, San Diego (UCSD) to explore new approaches to conversational recommendation systems. The key objectives of this 3-year project include: 1) Collecting new datasets for training and evaluating conversational models that can provide personalized...
This $174,995 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to understand and optimize the role of human intelligence in data integration and discovery pipelines, especially in the context of emerging large language models (LLMs) like ChatGPT. The project will investigate fundamental questions about human involvement in these data processes, uncover relevant human biases, and...
This Project Grant award of $763,741.00 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) supports a collaborative research project at New York University (NYU) to investigate how human and artificial intelligence (AI) language models, such as ChatGPT, process and understand language. The key goals of the project are to better understand the discrepancies between how humans and AI systems process temporary...
This two-year Project Grant from the National Science Foundation, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $166,937 to San Diego State University Research Foundation to support modeling of computer-mediated task-oriented dialogues using multi-modality information theoretic approaches. The Foundation will deliver research investigating the development and use of computational techniques to analyze multi-party, multi-modal conversations between...
This Project Grant award for $175,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports the development of a continual collaborative framework for knowledge graph reasoning. The project aims to address key challenges in knowledge graph reasoning, including reliability, sustainability, and extensibility, in order to advance open knowledge networks and strengthen their role as a vital component of the nation's...
This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program ($566,944) will support the development of purposeful conversational agents based on hierarchical knowledge graphs from September 1, 2022 to August 31, 2025. The awardee, the Research Foundation for the State University of New York, will create a fully functional conversational agent that incorporates factual knowledge, logical reasoning, and persuasive conversation strategies. The agent will engage in coherent, interesting discussions across several societal topics through the use of specially constructed multi-layered knowledge graphs and state-of-the-art neural response generators. Both automated and expert evaluations are planned to assess conversation quality and measure the agent's potential impact.