Monolingual word alignment is important for studying fine-grained editing operations (i.e., deletion, addition, and substitution) in text-to-text generation tasks, such as paraphrase generation, text simplification, neutralizing biased language, etc. In this paper, we present a novel neural semi-Markov CRF alignment model, which unifies word and phrase alignments through variable-length spans. We also create a new benchmark with human annotations that cover four different text genres to evaluate monolingual word alignment models in more realistic settings. Experimental results show that our proposed model outperforms all previous approaches for monolingual word alignment as well as a competitive QA-based baseline, which was previously only applied to bilingual data. Our model demonstrates good generalizability to three out-of-domain datasets and shows great utility in two downstream applications: automatic text simplification and sentence pair classification tasks.

提供了一种新的神经半-Markov CRF对齐模型，它通过可变长度跨度统一了单词和短语对齐，通过人工注释创建了一个新的基准，显示出在现实设置下评估单语言对齐模型的性能， 并证明了该模型在自动文本简化和句对分类任务中具有良好的普适性和实用性。

神经半-Markov CRF 用于单语词对齐