Event Graph based Sentence Fusion

Ruifeng Yuan, Zili Wang, Wenjie Li


Abstract
Sentence fusion is a conditional generation task that merges several related sentences into a coherent one, which can be deemed as a summary sentence. The importance of sentence fusion has long been recognized by communities in natural language generation, especially in text summarization. It remains challenging for a state-of-the-art neural abstractive summarization model to generate a well-integrated summary sentence. In this paper, we explore the effective sentence fusion method in the context of text summarization. We propose to build an event graph from the input sentences to effectively capture and organize related events in a structured way and use the constructed event graph to guide sentence fusion. In addition to make use of the attention over the content of sentences and graph nodes, we further develop a graph flow attention mechanism to control the fusion process via the graph structure. When evaluated on sentence fusion data built from two summarization datasets, CNN/DaliyMail and Multi-News, our model shows to achieve state-of-the-art performance in terms of Rouge and other metrics like fusion rate and faithfulness.
Anthology ID:
2021.emnlp-main.334
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4075–4084
Language:
URL:
https://aclanthology.org/2021.emnlp-main.334
DOI:
10.18653/v1/2021.emnlp-main.334
Bibkey:
Cite (ACL):
Ruifeng Yuan, Zili Wang, and Wenjie Li. 2021. Event Graph based Sentence Fusion. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4075–4084, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Event Graph based Sentence Fusion (Yuan et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.334.pdf
Software:
 2021.emnlp-main.334.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.334.mp4
Data
Multi-News