Corpus ID: 212658007

A Benchmark for Systematic Generalization in Grounded Language Understanding

@article{Ruis2020ABF,
  title={A Benchmark for Systematic Generalization in Grounded Language Understanding},
  author={Laura Ruis and Jacob Andreas and Marco Baroni and Diane Bouchacourt and B. Lake},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.05161}
}
Human language users easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret compositions unseen in training. In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in models of situated language understanding. We take inspiration from standard models of meaning composition in formal linguistics. Going… Expand
25 Citations
Think before you act: A simple baseline for compositional generalization
Improving Compositional Generalization in Semantic Parsing
Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
Systematic Generalization on gSCAN with Language Conditioned Embedding
Compositional Generalization via Neural-Symbolic Stack Machines
The EOS Decision and Length Extrapolation
Word meaning in minds and machines
...
1
2
3
...

References

SHOWING 1-10 OF 42 REFERENCES
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
The compositionality of neural networks: integrating symbolism and connectionism
Permutation Equivariant Models for Compositional Generalization in Language
Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks
Emergent Systematic Generalization in a Situated Agent
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Learning Compositional Rules via Neural Program Synthesis
...
1
2
3
4
5
...