arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.5693cs.CL
收藏

作为树转换的句子压缩

Sentence Compression as Tree Transduction

University of Edinburgh(爱丁堡大学)

Trevor Anthony Cohn, Mirella Lapata

摘要:

本文提出了一种用于句子压缩的树到树转换方法。我们的模型是基于同步树替换语法,一种形式主义,允许局部扭曲的树拓扑结构,从而可以自然地捕捉结构不匹配。我们描述了一个算法在这个框架中的解码,并显示了如何在一个大的利润框架内的模型可以进行训练的歧视。句子压缩的实验结果带来了显着的改进,在一个国家的最先进的模型。

英文摘要:

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framework. Experimental results on sentence compression bring significant improvements over a state-of-the-art model.

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。

↑