TY - GEN
T1 - Event Graph based Sentence Fusion
AU - Yuan, Ruifeng
AU - Wang, Zili
AU - Li, Wenjie
N1 - Funding Information:
The work described in this paper was supported by and Research Grants Council of Hong Kong(PolyU/15203617 and PolyU/5210919) and National Natural Science Foundation of China (61672445).
Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85127401515&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:85127401515
T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 4075
EP - 4084
BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -