Corpus ID: 225062282

SmBoP: Semi-autoregressive Bottom-up Semantic Parsing

@article{Rubin2020SmBoPSB,
  title={SmBoP: Semi-autoregressive Bottom-up Semantic Parsing},
  author={Ohad Rubin and Jonathan Berant},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.12412}
}
The de-facto standard decoding method for semantic parsing in recent years has been to autoregressively decode the abstract syntax tree of the target program using a top-down depth-first traversal. In this work, we propose an alternative approach: a Semi-autoregressive Bottom-up Parser (SmBoP) that constructs at decoding step $t$ the top-$K$ sub-trees of height $\leq t$. Our parser enjoys several benefits compared to top-down autoregressive parsing. First, since sub-trees in each decoding step… Expand
2 Citations

References

SHOWING 1-10 OF 35 REFERENCES
Reranking for Neural Semantic Parsing
  • 14
  • PDF
Global Reasoning over Database Structures for Text-to-SQL Parsing
  • 33
  • PDF
Learning Dependency-Based Compositional Semantics
  • 522
  • PDF
Weakly-supervised Semantic Parsing with Abstract Examples
  • 46
  • PDF
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
  • 136
  • PDF
Semantic Parsing on Freebase from Question-Answer Pairs
  • 1,047
  • PDF
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  • 15,621
  • PDF
Learning an Executable Neural Semantic Parser
  • 18
  • PDF
AllenNLP: A Deep Semantic Natural Language Processing Platform
  • 602
  • PDF
...
1
2
3
4
...