This lecture covers neural network-based syntactic parsing, focusing on graph-based parsing with iterative refinement. It discusses LSTM-based dependency score estimation, a neural graph-based dependency parser, and the G2GT iterative refinement parser. The lecture explains the EPEL motivation for finding graph structures, the RNGTr encoder architecture, and the iterative non-autoregressive refinement process. It introduces the Recursive Non-Autoregressive Graph-to-Graph Transformer (RNGTr) model, detailing the encoder and score function. The lecture also explores model selection, results on UD and Penn Treebanks, and the performance analysis based on dependency types and projectivity of dependency graphs.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace