Sentence Compression via DC Programming Approach
This work addresses sentence compression for natural language processing applications, presenting an incremental improvement through a hybrid method.
The authors tackled sentence compression by developing a model combining probability and parse tree models, equivalent to an integer linear program, and used a DC programming approach with parallel-branch-and-bound to find global optimal solutions, demonstrating good quality and excellent performance in numerical results.
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.