MLQA: Evaluating Cross-lingual Extractive Question Answering

@article{Lewis2020MLQAEC,
  title={MLQA: Evaluating Cross-lingual Extractive Question Answering},
  author={Patrick Lewis and Barlas Oguz and Ruty Rinott and Sebastian Riedel and Holger Schwenk},
  journal={ArXiv},
  year={2020},
  volume={abs/1910.07475}
}
  • Patrick Lewis, Barlas Oguz, +2 authors Holger Schwenk
  • Published 2020
  • Computer Science
  • ArXiv
  • Question answering (QA) models have shown rapid progress enabled by the availability of large, high-quality benchmark datasets. Such annotated datasets are difficult and costly to collect, and rarely exist in languages other than English, making training QA systems in other languages challenging. An alternative to building large monolingual training datasets is to develop cross-lingual systems which can transfer to a target language without requiring training data in that language. In order to… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 33 CITATIONS

    TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages

    VIEW 7 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    XPersona: Evaluating Multilingual Personalized Chatbot

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Unsupervised Cross-lingual Representation Learning at Scale

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    LAReQA: Language-agnostic answer retrieval from a multilingual pool

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    CITATION STATISTICS

    • 11 Highly Influenced Citations

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 74 REFERENCES

    Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

    VIEW 2 EXCERPTS