arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.02324cs.CL
收藏

文本简化中句子对齐的神经CRF模型

Neural CRF Model for Sentence Alignment in Text Simplification

The Ohio State University(俄亥俄州立大学)

Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu

摘要:

文本简化系统的成功与否很大程度上取决于训练语料库中复句-单句对的质量和数量,复句-单句对是通过对齐平行文章之间的句子来提取的。为了评估和提高句子对齐质量,我们从两个常用的文本简化语料库Newsela和Wikipedia中创建了两个手动注释的对齐数据集。我们提出了一种新的神经CRF对齐模型,它不仅利用了并行文档中句子的顺序性,而且还利用了神经句子对模型来捕获语义相似性。实验表明,我们提出的方法优于所有以前的单语句子对齐任务的F1超过5点。我们应用我们的CRF对齐器来构建两个新的文本简化数据集,Newsela-Auto和Wiki-Auto,与现有的数据集相比,它们更大,质量更好。在我们的数据集上训练的基于transformer的seq 2seq模型为自动和人工评估中的文本简化建立了一个新的最先进的技术。

英文摘要:

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, Newsela-Auto and Wiki-Auto, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation.

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。

↑