One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets
This addresses the fragmentation in semantic parsing datasets for NLP researchers, offering a more efficient and generalizable approach, though it is incremental in applying multi-task learning to this domain.
The authors tackled the problem of training a single semantic parser across multiple datasets with different meaning representations, achieving competitive or better parsing accuracies while reducing parameters by 68% and improving compositional generalization.
Semantic parsers map natural language utterances to meaning representations. The lack of a single standard for meaning representations led to the creation of a plethora of semantic parsing datasets. To unify different datasets and train a single model for them, we investigate the use of Multi-Task Learning (MTL) architectures. We experiment with five datasets (Geoquery, NLMaps, TOP, Overnight, AMR). We find that an MTL architecture that shares the entire network across datasets yields competitive or better parsing accuracies than the single-task baselines, while reducing the total number of parameters by 68%. We further provide evidence that MTL has also better compositional generalization than single-task models. We also present a comparison of task sampling methods and propose a competitive alternative to widespread proportional sampling strategies.