arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07064cs.CL
收藏

一切正常吗?排序句子的简单方法

Is Everything in Order? A Simple Way to Order Sentences

UNC Chapel Hill(北卡罗来纳大学教堂山分校);University of California, Santa Cruz(加利福尼亚大学圣克鲁兹分校)

Somnath Basu Roy Chowdhury, Faeze Brahman, Snigdha Chaturvedi

摘要:

将一组杂乱的句子组织成连贯的文本的任务已被用来评估机器对因果关系和时间关系的理解。我们制定的句子排序任务作为一个有条件的文本标记生成问题。我们提出了Reorder-BART(Re-BART),它利用预先训练的基于transformer的模型来识别给定的一组混洗句子的连贯顺序。该模型以一组具有特定于句子的标记的混洗句子作为输入,并在有序文本中生成句子的位置标记序列。Re-BART在完美匹配率(PMR)和Kendall's tau($τ$)中实现了7个数据集的最先进性能。我们在zero-shot设置中进行评估,表明我们的模型能够在其他数据集上很好地推广。我们还进行了几个实验,以了解我们的框架的功能和局限性。

英文摘要:

The task of organizing a shuffled set of sentences into a coherent text has been used to evaluate a machine's understanding of causal and temporal relations. We formulate the sentence ordering task as a conditional text-to-marker generation problem. We present Reorder-BART (Re-BART) that leverages a pre-trained Transformer-based model to identify a coherent order for a given set of shuffled sentences. The model takes a set of shuffled sentences with sentence-specific markers as input and generates a sequence of position markers of the sentences in the ordered text. Re-BART achieves the state-of-the-art performance across 7 datasets in Perfect Match Ratio (PMR) and Kendall's tau ($τ$). We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets. We additionally perform several experiments to understand the functioning and limitations of our framework.

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。

↑