A5086133623- Natural Language Processing Techniques
- Speech and dialogue systems
- Topic Modeling
- Innovative Teaching and Learning Methods
- Knowledge Management and Sharing
- Intelligent Tutoring Systems and Adaptive Learning
- Constraint Satisfaction and Optimization
- Multi-Agent Systems and Negotiation
- Software Engineering Techniques and Practices
- Educational Assessment and Pedagogy
- Education and Critical Thinking Development
- Speech Recognition and Synthesis
- AI-based Problem Solving and Planning
University of Colorado System
2020-2023
University of Colorado Boulder
2020-2023
In collaborative learning environments, effective intelligent systems need to accurately analyze and understand the discourse between learners (i.e., group modeling) provide adaptive support. We investigate how automatic speech recognition (ASR) errors influence models of small collaboration in noisy real-world classrooms. Our dataset consisted 30 students recorded by consumer off-the-shelf microphones (Yeti Blue) while engaging dyadic- triadic- a multi-day STEM curriculum unit. found that...
Spatial Reasoning from language is essential for natural understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in as well images and videos. Existing representations are not sufficient describing configurations used complex tasks. This paper extends the capabilities of existing languages increases coverage semantic aspects needed to ground meaning text world. Our relation able represent large, comprehensive set concepts crucial reasoning...
In recent decades, there has been a significant push to leverage technology aid both teachers and students in the classroom. Language processing advancements have harnessed provide better tutoring services, automated feedback teachers, improved peer-to-peer mechanisms, measures of student comprehension for reading. Automated question generation systems potential significantly reduce teachers' workload latter. this paper, we compare three differ- ent neural architectures across two types...
Jon Cai, Shafiuddin Rehan Ahmed, Julia Bonn, Kristin Wright-Bettner, Martha Palmer, James H. Martin. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2023.
We consider the problem of human-machine collaborative solving as a planning task coupled with natural language communication. Our framework consists three components -- engine that parses utterances to formal representation and vice-versa, concept learner induces generalized concepts for plans based on limited interactions user, an HTN planner solves human interaction. illustrate ability this address key challenges by demonstrating it building in Minecraft-based blocksworld domain. The...