Corpus ID: 212413976

Learning to Generate Multi-Hop Knowledge Paths for Commonsense Question Answering

@inproceedings{2020LearningTG,
  title={Learning to Generate Multi-Hop Knowledge Paths for Commonsense Question Answering},
  author={},
  year={2020}
}
  • Published 2020
  • Commonsense question answering (QA) requires a model of general background knowledge about how the world operates and how people interact with each other before reasoning. Prior works focus primarily on manually curated commonsense knowledge graphs, but these knowledge graphs are incomplete and thus may not contain the necessary knowledge for answering the questions. In this paper, we propose to learn a multi-hop knowledge path generator to generate structured evidence dynamically according to… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures and Tables from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Language Models are Unsupervised Multitask Learners

    VIEW 16 EXCERPTS
    HIGHLY INFLUENTIAL