排序句子和段落与预先训练的编码器-解码器变压器和指针集成

Rémi Calizzano, Malte Ostendorff, G. Rehm
{"title":"排序句子和段落与预先训练的编码器-解码器变压器和指针集成","authors":"Rémi Calizzano, Malte Ostendorff, G. Rehm","doi":"10.1145/3469096.3469874","DOIUrl":null,"url":null,"abstract":"Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task from sentences to paragraphs, i.e., passages with multiple sentences. Increasing the passage length increases the task's difficulty. To account for this, we propose the combination of a pre-trained encoder-decoder Transformer model, namely BART, with variations of pointer networks. We empirically evaluate the proposed models for sentence and paragraph ordering. Our best model outperforms previous state of the art methods by 0.057 Kendall's Tau on one of three sentence ordering benchmarks (arXiv, VIST, ROC-Story). For paragraph ordering, we construct two novel datasets from Wikipedia and CNN-DailyMail on which we achieve 0.67 and 0.47 Kendall's Tau. The best model variation utilises multiple pointer networks in an ensemble-like fashion. We hypothesise that the use of multiple pointers better reflects the multitude of possible orders of paragraphs in more complex texts. Our code, data, and models are publicly available1.","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"68 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Ordering sentences and paragraphs with pre-trained encoder-decoder transformers and pointer ensembles\",\"authors\":\"Rémi Calizzano, Malte Ostendorff, G. Rehm\",\"doi\":\"10.1145/3469096.3469874\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task from sentences to paragraphs, i.e., passages with multiple sentences. Increasing the passage length increases the task's difficulty. To account for this, we propose the combination of a pre-trained encoder-decoder Transformer model, namely BART, with variations of pointer networks. We empirically evaluate the proposed models for sentence and paragraph ordering. Our best model outperforms previous state of the art methods by 0.057 Kendall's Tau on one of three sentence ordering benchmarks (arXiv, VIST, ROC-Story). For paragraph ordering, we construct two novel datasets from Wikipedia and CNN-DailyMail on which we achieve 0.67 and 0.47 Kendall's Tau. The best model variation utilises multiple pointer networks in an ensemble-like fashion. We hypothesise that the use of multiple pointers better reflects the multitude of possible orders of paragraphs in more complex texts. Our code, data, and models are publicly available1.\",\"PeriodicalId\":423462,\"journal\":{\"name\":\"Proceedings of the 21st ACM Symposium on Document Engineering\",\"volume\":\"68 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 21st ACM Symposium on Document Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3469096.3469874\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 21st ACM Symposium on Document Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3469096.3469874","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

段落排序的目的是在文档生成或文档修改任务(如总结或讲故事)中最大限度地提高话语一致性。本文将文章排序任务从句子扩展到段落,即包含多个句子的段落。增加通道长度会增加任务的难度。为了解释这一点,我们建议将预训练的编码器-解码器转换器模型(即BART)与指针网络的变化相结合。我们对所提出的句子和段落排序模型进行了实证评估。我们最好的模型在三个句子排序基准(arXiv, VIST, ROC-Story)中的一个上比以前最先进的方法高出0.057 Kendall's Tau。对于段落排序,我们构建了两个来自维基百科和CNN-DailyMail的新数据集,其肯德尔Tau值分别为0.67和0.47。最好的模型变体以类似集成的方式利用多个指针网络。我们假设,在更复杂的文本中,使用多个指针可以更好地反映多种可能的段落顺序。我们的代码、数据和模型都是公开可用的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Ordering sentences and paragraphs with pre-trained encoder-decoder transformers and pointer ensembles
Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task from sentences to paragraphs, i.e., passages with multiple sentences. Increasing the passage length increases the task's difficulty. To account for this, we propose the combination of a pre-trained encoder-decoder Transformer model, namely BART, with variations of pointer networks. We empirically evaluate the proposed models for sentence and paragraph ordering. Our best model outperforms previous state of the art methods by 0.057 Kendall's Tau on one of three sentence ordering benchmarks (arXiv, VIST, ROC-Story). For paragraph ordering, we construct two novel datasets from Wikipedia and CNN-DailyMail on which we achieve 0.67 and 0.47 Kendall's Tau. The best model variation utilises multiple pointer networks in an ensemble-like fashion. We hypothesise that the use of multiple pointers better reflects the multitude of possible orders of paragraphs in more complex texts. Our code, data, and models are publicly available1.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信