arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.13449cs.CL
收藏

受控文本缩减

Controlled Text Reduction

Bar-Ilan University(巴伊兰大学)

Aviv Slobodkin, Paul Roit, Eran Hirsch, Ori Ernst, Ido Dagan

摘要:

生成源文本的精简版本,例如通用或重点摘要,本质上涉及两个不同的子任务:决定目标内容并生成传达该内容的连贯文本。虽然一些流行的方法将摘要作为单个端到端任务来处理,但著名的作品支持对各个子任务进行分解建模。此外,半自动文本缩减也非常有吸引力,其中用户可以识别目标内容,而模型将生成相应的连贯摘要。在本文中,我们专注于第二子任务,生成连贯的文本给定的预选内容。具体地说,我们将\textit{Controlled Text Reduction}形式化为一个独立的任务,其输入是一个带有目标内容标记跨度(“突出显示”)的源文本。然后,模型需要生成一个连贯的文本,其中包括所有且仅包括目标信息。我们提倡这种模型的潜力,无论是模块化的全自动摘要,以及半自动人在回路用例。为了促进适当的研究,我们为任务众包高质量的开发和测试数据集。此外,我们利用预训练的摘要-源对齐模型,从可用的摘要基准自动生成更大的“银色”训练数据集。最后,利用这些数据集,我们提出了一个监督基线模型,显示出有希望的结果和有见地的分析。

英文摘要:

Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address summarization as a single end-to-end task, prominent works support decomposed modeling for individual subtasks. Further, semi-automated text reduction is also very appealing, where users may identify targeted content while models would generate a corresponding coherent summary. In this paper, we focus on the second subtask, of generating coherent text given pre-selected content. Concretely, we formalize \textit{Controlled Text Reduction} as a standalone task, whose input is a source text with marked spans of targeted content ("highlighting"). A model then needs to generate a coherent text that includes all and only the target information. We advocate the potential of such models, both for modular fully-automatic summarization, as well as for semi-automated human-in-the-loop use cases. Facilitating proper research, we crowdsource high-quality dev and test datasets for the task. Further, we automatically generate a larger "silver" training dataset from available summarization benchmarks, leveraging a pretrained summary-source alignment model. Finally, employing these datasets, we present a supervised baseline model, showing promising results and insightful analyses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑