Corpus ID: 209202200

Neural Module Networks for Reasoning over Text

@article{Gupta2020NeuralMN,
  title={Neural Module Networks for Reasoning over Text},
  author={Nitish Gupta and Kevin Lin and D. Roth and Sameer Singh and Matt Gardner},
  journal={ArXiv},
  year={2020},
  volume={abs/1912.04971}
}
  • Nitish Gupta, Kevin Lin, +2 authors Matt Gardner
  • Published 2020
  • Computer Science
  • ArXiv
  • Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable programs composed of learnable modules, performing well on synthetic visual QA domains. However, we find that it is challenging to learn these models for non-synthetic questions on open-domain text, where a model needs to deal with the diversity of natural… CONTINUE READING
    24 Citations

    Figures, Tables, and Topics from this paper

    Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning
    • Highly Influenced
    • PDF
    Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
    • 2
    • Highly Influenced
    • PDF
    Obtaining Faithful Interpretations from Compositional Neural Networks
    • 7
    • PDF
    Understanding Unnatural Questions Improves Reasoning over Text
    • Highly Influenced
    • PDF
    Teaching Machine Comprehension with Compositional Explanations
    • 2
    • PDF
    Multi-Step Inference for Reasoning Over Paragraphs
    • 3
    • PDF
    KQA Pro: A Large Diagnostic Dataset for Complex Question Answering over Knowledge Base
    • 2
    Human Explanation-based Learning for Machine Comprehension
    • PDF
    Learning from Task Descriptions
    • 3
    • PDF

    References

    SHOWING 1-10 OF 29 REFERENCES
    Learning to Reason: End-to-End Module Networks for Visual Question Answering
    • 334
    • PDF
    Neural Compositional Denotational Semantics for Question Answering
    • 11
    • PDF
    Learning a Natural Language Interface with Neural Programmer
    • 109
    • PDF
    Neural Module Networks
    • 544
    • PDF
    Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
    • 131
    • PDF
    DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
    • 166
    • Highly Influential
    • PDF
    A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
    • 23
    • Highly Influential
    • PDF
    CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
    • 761
    • Highly Influential
    • PDF
    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
    • 14,559
    • PDF
    CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
    • 172
    • PDF