基于神经半马尔可夫CRF的单语词对齐
Neural semi-Markov CRF for Monolingual Word Alignment
摘要：
单语单词对齐对于研究细粒度编辑操作（即，删除，添加和替换）在文本到文本生成任务，如释义生成，文本简化，中和偏见的语言等，在本文中，我们提出了一种新的神经半马尔可夫CRF对齐模型，通过可变长度跨度统一的单词和短语对齐。我们还创建了一个新的基准与人类注释，涵盖四种不同的文本类型，以评估单语词对齐模型在更现实的设置。实验结果表明，我们提出的模型优于所有以前的单语词对齐方法，以及竞争性的基于QA的基线，这是以前只适用于双语数据。我们的模型对三个域外数据集表现出良好的泛化能力，并在两个下游应用中表现出很大的实用性：自动文本简化和句子对分类任务。
英文摘要：
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.
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。
