Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining
Grigorii Guz, Patrick Huber, Giuseppe Carenini
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale "silver-standard" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Instructional-DT (Instr-DT) | Guz et al. (2020) (pretrained) | Standard Parseval (Nuclearity) | 46.59 | — | Unverified |
| Instructional-DT (Instr-DT) | Guz et al. (2020) | Standard Parseval (Nuclearity) | 44.41 | — | Unverified |
| RST-DT | Guz et al. (2020) (pretrained) | Standard Parseval (Span) | 72.94 | — | Unverified |
| RST-DT | Guz et al. (2020) | Standard Parseval (Span) | 72.43 | — | Unverified |