Corpus ID: 207847496

Contextualized Sparse Representation with Rectified N-Gram Attention for Open-Domain Question Answering

@article{Lee2019ContextualizedSR,
  title={Contextualized Sparse Representation with Rectified N-Gram Attention for Open-Domain Question Answering},
  author={Jinhyuk Lee and Minjoon Seo and Hannaneh Hajishirzi and Jaewoo Kang},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.02896}
}
  • Jinhyuk Lee, Minjoon Seo, +1 author Jaewoo Kang
  • Published in ArXiv 2019
  • Computer Science
  • A sparse representation is known to be an effective means to encode precise lexical cues in information retrieval tasks by associating each dimension with a unique n-gram-based feature. However, it has often relied on term frequency (such as tf-idf and BM25) or hand-engineered features that are coarse-grained (document-level) and often task-specific, hence not easily generalizable and not appropriate for fine-grained (word or phrase-level) retrieval. In this work, we propose an effective method… CONTINUE READING

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

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES

    End-to-End Open-Domain Question Answering with BERTserini

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL