An abstractive approach to sentence compression
An abstractive approach to sentence compression
复制标题
DOI：
10.1145/2483669.2483674
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Trevor Cohn;Mirella Lapata
中科院分区：
文献类型：
--
作者：
Trevor Cohn;Mirella Lapata
在本文中，我们概括了句子压缩任务。与以前的工作不同，我们不是简单地通过删除单词或成分来缩短句子，而是使用其他操作，如替换、重新排序和插入来重写句子。我们提出的一项实验研究表明，人类可以自然地使用各种重写操作来创建抽象句子，而不仅仅是删除。接下来，我们创建一个适合抽象压缩任务的新语料库，并建立一个能够解释结构和词汇不匹配的区分树到树的转换模型。该模型结合了语法提取方法，使用用于相干输出的语言模型，并且可以很容易地调整到广泛的压缩特定损失函数。
In this article we generalize the sentence compression task. Rather than simply shorten a sentence by deleting words or constituents, as in previous work, we rewrite it using additional operations such as substitution, reordering, and insertion. We present an experimental study showing that humans can naturally create abstractive sentences using a variety of rewrite operations, not just deletion. We next create a new corpus that is suited to the abstractive compression task and formulate a discriminative tree-to-tree transduction model that can account for structural and lexical mismatches. The model incorporates a grammar extraction method, uses a language model for coherent output, and can be easily tuned to a wide range of compression-specific loss functions.