Yichu Zhou

A Simple Global Neural Discourse Parser

2020 · arXiv (Cornell University)

Discourse parsing is largely dominated by greedy parsers with manually-designed features, while global parsing is rare due to its computational expense. In this paper, we propose a simple chart-based neural discourse parser that does not …

DirectProbe: Studying Representations without Classifiers

2021 · arXiv (Cornell University)

Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@. Existing approaches for probing them usually call for training classifiers and use the accuracy, mutual information, or complexity …