Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming

Litton J Kurisinkel, Nancy Chen


Abstract
One key challenge in multi-document summarization is the generated summary is often less coherent compared to single document summarization due to the larger heterogeneity of the input source content. In this work, we propose a generic framework to jointly consider coherence and informativeness in multi-document summarization and offers provisions to replace individual components based on the domain of source text. In particular, the framework characterizes coherence through verb transitions and entity mentions and takes advantage of syntactic parse trees and neural modeling for intra-sentential noise pruning. The framework cast the entire problem as an integer linear programming optimization problem with neural and non-neural models as linear components. We evaluate our method in the news and legal domains. The proposed approach consistently performs better than competitive baselines for both objective metrics and human evaluation.
Anthology ID:
2022.emnlp-industry.24
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2022
Address:
Abu Dhabi, UAE
Editors:
Yunyao Li, Angeliki Lazaridou
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
237–243
Language:
URL:
https://aclanthology.org/2022.emnlp-industry.24
DOI:
10.18653/v1/2022.emnlp-industry.24
Bibkey:
Cite (ACL):
Litton J Kurisinkel and Nancy Chen. 2022. Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 237–243, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming (J Kurisinkel & Chen, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-industry.24.pdf