A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification

A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification
复制标题

一种基于非自回归编辑的可控文本简化方法

DOI:
10.18653/v1/2021.findings-acl.330
复制
发表时间:
2021
期刊:
Proceedings of the CHI Conference on Human Factors in Computing Systems
影响因子:
--
通讯作者:
Marine Carpuat
Marine Carpuat
中科院分区:
--
文献类型:
--
作者:
Sweta Agrawal;Weijia Xu;Marine Carpuat

文献摘要

参考文献

被引文献

相似文献

我们引入了一种新的方法来完成可控文本简化的任务,即系统重写一个复杂的英语句子,以便美国K-12系统中不同年级的读者都能理解。它使用非自回归模型来迭代编辑输入序列,并将词汇复杂度信息无缝地整合到精化过程中,以生成比强自回归基线更好地匹配所需输出复杂度的简化。分析表明,我们的模型的本地编辑操作相结合,以实现更复杂的简化操作,如内容删除和释义,以及句子分裂。
We introduce a new approach for the task of Controllable Text Simplification, where systems rewrite a complex English sentence so that it can be understood by readers at different grade levels in the US K-12 system. It uses a non-autoregressive model to iteratively edit an input sequence and incorporates lexical complexity information seamlessly into the refinement process to generate simplifications that better match the desired output complexity than strong autoregressive baselines. Analysis shows that our model’s local edit operations are combined to achieve more complex sim-plification operations such as content deletion and paraphrasing, as well as sentence splitting.
DOI: 10.18653/v1/2021.findings-acl.455
发表时间: 2020-10
期刊: --
影响因子: --
作者:
Neha Srikanth;Junyi Jessy Li
通讯作者: Neha Srikanth;Junyi Jessy Li