Tiantian Han
Papers
1
Total Citations
11
H-Index
1
About
Tiantian Han is a rising researcher at the forefront of natural language processing and data mining for scientific literature. Her primary research focuses on developing unsupervised, label-free methods to extract structured information from vast, unstructured text corpora, with a particular emphasis on chemical and materials science domains. Han’s most notable contribution is the introduction of unsupervised syntactic distance analysis (SDA), a novel approach that autonomously identifies chemical substances, their functions, and proper names from scientific papers without requiring labeled training data. This work, published in 2023 and already garnering 11 citations, addresses a critical bottleneck in feeding high-quality, machine-readable data into AI systems for accelerated discovery. By eliminating the need for manual annotation, Han’s method promises to unlock the full potential of the ever-growing scientific literature, enabling researchers to efficiently mine knowledge at scale. Her innovative approach positions her as a key figure in the movement toward automated, AI-driven scientific analysis, with potential impacts spanning drug discovery, materials design, and beyond.
Research Focus
Key Achievements
Top Papers
- 1