#ABCD CHART MODS#
Cite (Informal): ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences (Gao et al., ACL-IJCNLP 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: Code serenayj/ABCD-ACL2021Īdditional community = ": A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences",īooktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)", Association for Computational Linguistics. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3919–3931, Online. ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences. IJCNLP SIG: Publisher: Association for Computational Linguistics Note: Pages: 3919–3931 Language: URL: DOI: 10.18653/v1/2021.acl-long.303 Bibkey: gao-etal-2021-abcd Cite (ACL): Yanjun Gao, Ting-Hao Huang, and Rebecca J. Anthology ID: 2021.acl-long.303 Volume: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Month: August Year: 2021 Address: Online Venues: ACL Results include a detailed error analysis. On DeSSE, which has a more even balance of complex sentence types, our model achieves higher accuracy on the number of atomic sentences than an encoder-decoder baseline. ABCD achieves comparable performance as two parsing baselines on MinWiki. We introduce DeSSE, a new dataset designed to train and evaluate complex sentence decomposition, and MinWiki, a subset of MinWikiSplit.
#ABCD CHART FULL#
The full processing pipeline includes modules for graph construction, graph editing, and sentence generation from the output graph. Our neural model learns to Accept, Break, Copy or Drop elements of a graph that combines word adjacency and grammatical dependencies. We propose a new task to decompose each complex sentence into simple sentences derived from the tensed clauses in the source, and a novel problem formulation as a graph edit task. Previous work mainly relies on rule-based methods dependent on parsing. Identifying the atomic sentences within complex sentences is important for applications such as summarization, argument mining, discourse analysis, discourse parsing, and question answering. Abstract Atomic clauses are fundamental text units for understanding complex sentences.
0 kommentar(er)
