Paras Jain

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

2021 · arXiv (Cornell University)

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax context. …

Accelerating Software Development with Artificial Intelligence

2024

Software development is experiencing a significant transformation driven by Artificial Intelligence. The demand for high-quality software is ever-growing. Traditional software development can be time-consuming, often bottlenecked by repetitive tasks and the need to write vast …