The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing

摘要

We evaluate a semantic parser based on a character-based sequence-to-sequencemodel in the context of the SemEval-2017 shared task on semantic parsing forAMRs. With data augmentation, super characters, and POS-tagging we gain majorimprovements in performance compared to a baseline character-level model.Although we improve on previous character-based neural semantic parsing models,the overall accuracy is still lower than a state-of-the-art AMR parser. Anensemble combining our neural semantic parser with an existing, traditionalparser, yields a small gain in performance.