Neural Generative Rhetorical Structure Parsing

Amandla Mabona, Laura Rimell, Stephen Clark, Andreas Vlachos


Abstract
Rhetorical structure trees have been shown to be useful for several document-level tasks including summarization and document classification. Previous approaches to RST parsing have used discriminative models; however, these are less sample efficient than generative models, and RST parsing datasets are typically small. In this paper, we present the first generative model for RST parsing. Our model is a document-level RNN grammar (RNNG) with a bottom-up traversal order. We show that, for our parser’s traversal order, previous beam search algorithms for RNNGs have a left-branching bias which is ill-suited for RST parsing. We develop a novel beam search algorithm that keeps track of both structure-and word-generating actions without exhibit-ing this branching bias and results in absolute improvements of 6.8 and 2.9 on unlabelled and labelled F1 over previous algorithms. Overall, our generative model outperforms a discriminative model with the same features by 2.6 F1points and achieves performance comparable to the state-of-the-art, outperforming all published parsers from a recent replication study that do not use additional training data
Anthology ID:
D19-1233
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2284–2295
Language:
URL:
https://aclanthology.org/D19-1233
DOI:
10.18653/v1/D19-1233
Bibkey:
Cite (ACL):
Amandla Mabona, Laura Rimell, Stephen Clark, and Andreas Vlachos. 2019. Neural Generative Rhetorical Structure Parsing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2284–2295, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Neural Generative Rhetorical Structure Parsing (Mabona et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1233.pdf