Corpus ID: 222291650

Improving Compositional Generalization in Semantic Parsing

  title={Improving Compositional Generalization in Semantic Parsing},
  author={Inbar Oren and Jonathan Herzig and Nitish Gupta and Matt Gardner and Jonathan Berant},
  • Inbar Oren, Jonathan Herzig, +2 authors Jonathan Berant
  • Published in EMNLP 2020
  • Computer Science
  • Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked substantial interest. In this work, we investigate compositional generalization in semantic parsing, a natural test-bed for compositional generalization, as output programs are constructed from sub-components. We analyze a wide variety of… CONTINUE READING
    1 Citations

    Figures and Tables from this paper.


    Data Recombination for Neural Semantic Parsing
    • 257
    • PDF
    Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
    • 121
    • PDF
    Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples
    • 26
    • PDF
    Neural Module Networks for Reasoning over Text
    • 22
    • PDF
    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
    • 11,729
    • Highly Influential
    • PDF
    CLOSURE: Assessing Systematic Generalization of CLEVR Models
    • 13
    • PDF
    A Benchmark for Systematic Generalization in Grounded Language Understanding
    • 12
    • PDF
    Learning to generalize to new compositions in image understanding
    • 43
    • PDF
    Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
    • 49
    • PDF