Corpus ID: 44098100

KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings

@article{Zhang2018KG2LT,
  title={KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings},
  author={Y. Zhang and Hanjun Dai and Kamil Toraman and L. Song},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.12393}
}
  • Y. Zhang, Hanjun Dai, +1 author L. Song
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to significantly outperform random baseline, reflecting the difficult nature of this task. In this paper, we propose a novel framework for answering science exam questions, which… CONTINUE READING
    18 Citations

    Figures, Tables, and Topics from this paper

    Answering Science Exam Questions Using Query Rewriting with Background Knowledge
    • 5
    • Highly Influenced
    • PDF
    Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
    • 9
    • PDF
    Learning Contextualized Knowledge Structures for Commonsense Reasoning
    • 1
    • PDF
    Improving Retrieval-Based Question Answering with Deep Inference Models
    • 5
    • PDF
    Improving Question Answering by Commonsense-Based Pre-Training
    • 28
    • Highly Influenced
    • PDF
    Careful Selection of Knowledge to Solve Open Book Question Answering
    • 21
    • PDF
    Alignment over Heterogeneous Embeddings for Question Answering
    • 10
    • PDF
    Improving Question Answering with External Knowledge
    • 24
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 22 REFERENCES
    Variational Reasoning for Question Answering with Knowledge Graph
    • 121
    • PDF
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
    • 164
    • Highly Influential
    • PDF
    Question Answering via Integer Programming over Semi-Structured Knowledge
    • 74
    • PDF
    Answering Complex Questions Using Open Information Extraction
    • 67
    • PDF
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,495
    • PDF
    SciTaiL: A Textual Entailment Dataset from Science Question Answering
    • 175
    • Highly Influential
    Markov Logic Networks for Natural Language Question Answering
    • 18
    • PDF
    Bidirectional Attention Flow for Machine Comprehension
    • 1,254
    • PDF
    GAKE: Graph Aware Knowledge Embedding
    • 53
    • PDF