![]() This paper introduces affinity-preserving random walk to the summarization task, which preserves the affinity relations of sentences by an absorbing random walk model. Publisher = "Association for Computational Linguistics",Ībstract = "Multi-document summarization provides users with a short text that summarizes the information in a set of related documents. Cite (Informal): Affinity-Preserving Random Walk for Multi-Document Summarization (Wang et al., EMNLP 2017) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: = "Affinity-Preserving Random Walk for Multi-Document Summarization",īooktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing", Association for Computational Linguistics. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 210–220, Copenhagen, Denmark. Affinity-Preserving Random Walk for Multi-Document Summarization. Anthology ID: D17-1020 Volume: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing Month: September Year: 2017 Address: Copenhagen, Denmark Venue: EMNLP SIG: SIGDAT Publisher: Association for Computational Linguistics Note: Pages: 210–220 Language: URL: DOI: 10.18653/v1/D17-1020 Bibkey: wang-etal-2017-affinity Cite (ACL): Kexiang Wang, Tianyu Liu, Zhifang Sui, and Baobao Chang. The ROUGE evaluations on DUC 2003 topic-focused summarization task and DUC 2004 generic summarization task show the good performance of our method, which has the best ROUGE-2 recall among the graph-based ranking methods. ![]() Meanwhile, we put forward adjustable affinity-preserving random walk to enforce the diversity constraint of summarization in the random walk process. ![]() Abstract Multi-document summarization provides users with a short text that summarizes the information in a set of related documents.
0 Comments
Leave a Reply. |