Worth Their Weights? Evaluating Generative Models for Discourse Parsing
Abstract
Rhetorical Structure Theory (RST) parsing has historically been dominated by discriminative models based on pretrained encoder-only language models. The recent availability of high-quality generative language models has made it unclear whether RST parsing is better approached as a generative task. In this work, we investigate whether generative language models are better at parsing RST than traditional discriminative ones. We find that at matched parameter counts, discriminative parsers perform much better than generative ones, though much larger generative models sometimes outperform them. Generative models hold a particular advantage in elementary discourse unit (EDU) segmentation, and we report new state-of-the-art results on the RST-DT benchmark in end-to-end parsing as well as segmentation.
Get this paper in your agent:
hf papers read 2610.17658 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 12
larc-iu/dmrst-xlm-roberta-base-gcdt
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper