Natural Language to Structured Query Generation via Meta-Learning

@inproceedings{Huang2018NaturalLT,
  title={Natural Language to Structured Query Generation via Meta-Learning},
  author={Po-Sen Huang and Chenglong Wang and Rishabh Singh and Wen-tau Yih and Xiaodong He},
  booktitle={NAACL-HLT},
  year={2018}
}
In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats each example as a unique pseudo-task, by reducing the original learning problem to a few-shot meta-learning scenario with the help of a domain-dependent relevance function. When evaluated on the WikiSQL dataset, our approach leads to… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS

Meta Reasoning over Knowledge Graphs

Hong Wang, Wenhan Xiong, +3 authors William Yang Wang
  • ArXiv
  • 2019
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

1 Multi-Modal Synthesis of Regular Expressions

Greg Durrett, Isil Dillig
  • 2019
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.