AMR-to-text generation as a Traveling Salesman Problem
This work addresses the problem of generating grammatical text from AMR graphs for natural language processing applications, presenting an incremental approach.
The authors tackled AMR-to-text generation by partitioning the AMR graph into fragments, generating translations for each, and ordering them via an asymmetric generalized traveling salesman problem, achieving a BLEU score of 22.44 on the SemEval-2016 Task8 dataset.
The task of AMR-to-text generation is to generate grammatical text that sustains the semantic meaning for a given AMR graph. We at- tack the task by first partitioning the AMR graph into smaller fragments, and then generating the translation for each fragment, before finally deciding the order by solving an asymmetric generalized traveling salesman problem (AGTSP). A Maximum Entropy classifier is trained to estimate the traveling costs, and a TSP solver is used to find the optimized solution. The final model reports a BLEU score of 22.44 on the SemEval-2016 Task8 dataset.