We demonstrate experimentally on two benchmark datasets that our summarizer performs competitively against state-of-the-art methods.Download the dataset (distributed under the CC BY-SA 4.0 license): We design a new iterative refinement algorithm: it induces the trees through repeatedly refining the structures predicted by previous iterations. Each root node in the tree is a summary sentence, and the subtrees attached to it are sentences whose content relates to or explains the summary sentence. In contrast to previous approaches which have relied on linguistically motivated document representations to generate summaries, our model induces a multi-root dependency tree while predicting the output summary. %X In this paper, we conceptualize single-document extractive summarization as a tree induction problem. %I Association for Computational Linguistics %S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) %T Single Document Summarization as Tree Induction We demonstrate experimentally on two benchmark datasets that our summarizer performs competitively against state-of-the-art methods. In this paper, we conceptualize single-document extractive summarization as a tree induction problem. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)Īssociation for Computational Linguistics Single Document Summarization as Tree Induction We demonstrate experimentally on two benchmark datasets that our summarizer performs competitively against state-of-the-art methods.", Publisher = "Association for Computational Linguistics",Ībstract = "In this paper, we conceptualize single-document extractive summarization as a tree induction problem. Cite (Informal): Single Document Summarization as Tree Induction (Liu et al., NAACL 2019) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Code = "Single Document Summarization as Tree Induction",īooktitle = "Proceedings of the 2019 Conference of the North merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", Association for Computational Linguistics. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1745–1755, Minneapolis, Minnesota. Single Document Summarization as Tree Induction. Anthology ID: N19-1173 Volume: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) Month: June Year: 2019 Address: Minneapolis, Minnesota Venue: NAACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 1745–1755 Language: URL: DOI: 10.18653/v1/N19-1173 Bibkey: liu-etal-2019-single Cite (ACL): Yang Liu, Ivan Titov, and Mirella Lapata. Abstract In this paper, we conceptualize single-document extractive summarization as a tree induction problem.
0 Comments
Leave a Reply. |