The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing
This work addresses semantic parsing for natural language processing researchers, but it is incremental as it builds on existing methods and does not surpass top performance.
The paper tackled semantic parsing for Abstract Meaning Representations (AMRs) using a character-based sequence-to-sequence model with data augmentation and other techniques, achieving major improvements over a baseline but lower accuracy than state-of-the-art parsers, with an ensemble providing a small gain.
We evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval-2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and POS-tagging we gain major improvements 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. An ensemble combining our neural semantic parser with an existing, traditional parser, yields a small gain in performance.