arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.07248cs.CLmath.OC
收藏

基于DC编程的句子压缩

Sentence Compression via DC Programming Approach

Shanghai Jiao Tong University(上海交通大学);SJTU-Paristech Elite Institute of Technology(上海交通大学巴黎高科卓越工程师学院)

Yi-Shuai Niu, Xi-Wei Hu, Yu You, Faouzi Mohamed Benammour, Hu Zhang

摘要:

句子压缩是自然语言处理中的一个重要问题。本文首先基于概率模型和句法分析树模型建立了一种新的句子压缩模型。我们的句子压缩模型等价于一个整数线性规划(ILP),既能保证压缩的语法正确性,又能保存句子的主要意思。我们建议使用DC(凸差分)规划方法(DCA)寻找我们的模型的局部最优解。将DCA与并行分支定界框架相结合,可以得到全局最优解。数值结果表明,我们的句子压缩模型的质量和我们提出的解决方案的算法的优异性能。

英文摘要:

Sentence compression is an important problem in natural language processing. In this paper, we firstly establish a new sentence compression model based on the probability model and the parse tree model. Our sentence compression model is equivalent to an integer linear program (ILP) which can both guarantee the syntax correctness of the compression and save the main meaning. We propose using a DC (Difference of convex) programming approach (DCA) for finding local optimal solution of our model. Combing DCA with a parallel-branch-and-bound framework, we can find global optimal solution. Numerical results demonstrate the good quality of our sentence compression model and the excellent performance of our proposed solution algorithm.

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。

↑