Bookmark Saya

arXiv Open Access 2021

DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension

Jiaqi Li Ming Liu Zihao Zheng Heng Zhang Bing Qin +2 lainnya
Lihat Sumber

Abstrak

Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC. To fully exploit such discourse structure in multiparty dialogue, we present a discourse-aware dialogue graph neural network, DADgraph, which explicitly constructs the dialogue graph using discourse dependency links and discourse relations. To validate our model, we perform experiments on the Molweni corpus, a large-scale MRC dataset built over multiparty dialogue annotated with discourse structure. Experiments on Molweni show that our discourse-aware model achieves statistically significant improvements compared against strong neural network MRC baselines.

Topik & Kata Kunci

cs.CL

Penulis (7)

J

Jiaqi Li

M

Ming Liu

Z

Zihao Zheng

H

Heng Zhang

B

Bing Qin

M

Min-Yen Kan

T

Ting Liu

Format Sitasi

APA MLA BibTeX
Li, J., Liu, M., Zheng, Z., Zhang, H., Qin, B., Kan, M. et al. (2021). DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension. https://arxiv.org/abs/2104.12377

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓