A Neural Graph-based Local Coherence Model

Mohsen Mesgar, Leonardo F. R. Ribeiro, Iryna Gurevych


Abstract
Entity grids and entity graphs are two frameworks for modeling local coherence. These frameworks represent entity relations between sentences and then extract features from such representations to encode coherence. The benefits of convolutional neural models for extracting informative features from entity grids have been recently studied. In this work, we study the benefits of Relational Graph Convolutional Networks (RGCN) to encode entity graphs for measuring local coherence. We evaluate our neural graph-based model for two benchmark coherence evaluation tasks: sentence ordering (SO) and summary coherence rating (SCR). The results show that our neural graph-based model consistently outperforms the neural grid-based model for both tasks. Our model performs competitively with a strong baseline coherence model, while our model uses 50% fewer parameters. Our work defines a new, efficient, and effective baseline for local coherence modeling.
Anthology ID:
2021.findings-emnlp.199
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2316–2321
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.199
DOI:
10.18653/v1/2021.findings-emnlp.199
Bibkey:
Cite (ACL):
Mohsen Mesgar, Leonardo F. R. Ribeiro, and Iryna Gurevych. 2021. A Neural Graph-based Local Coherence Model. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2316–2321, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Neural Graph-based Local Coherence Model (Mesgar et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.199.pdf