arXiv Open Access 2025

Bridging Discourse Treebanks with a Unified Rhetorical Structure Parser

Elena Chistova
Lihat Sumber

Abstrak

We introduce UniRST, the first unified RST-style discourse parser capable of handling 18 treebanks in 11 languages without modifying their relation inventories. To overcome inventory incompatibilities, we propose and evaluate two training strategies: Multi-Head, which assigns separate relation classification layer per inventory, and Masked-Union, which enables shared parameter training through selective label masking. We first benchmark monotreebank parsing with a simple yet effective augmentation technique for low-resource settings. We then train a unified model and show that (1) the parameter efficient Masked-Union approach is also the strongest, and (2) UniRST outperforms 16 of 18 mono-treebank baselines, demonstrating the advantages of a single-model, multilingual end-to-end discourse parsing across diverse resources.

Topik & Kata Kunci

Penulis (1)

E

Elena Chistova

Format Sitasi

Chistova, E. (2025). Bridging Discourse Treebanks with a Unified Rhetorical Structure Parser. https://arxiv.org/abs/2510.06427

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓