Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer

@inproceedings{Mackova2020ReadingCI,
  title={Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer},
  author={Katevrina Mackov'a and Milan Straka},
  booktitle={TDS},
  year={2020}
}
  • Katevrina Mackov'a, Milan Straka
  • Published in TDS 2020
  • Computer Science
  • Reading comprehension is a well studied task, with huge training datasets in English. This work focuses on building reading comprehension systems for Czech, without requiring any manually annotated Czech training data. First of all, we automatically translated SQuAD 1.1 and SQuAD 2.0 datasets to Czech to create training and development data, which we release at this http URL. We then trained and evaluated several BERT and XLM-RoBERTa baseline models. However, our main focus lies in cross… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    SHOWING 1-10 OF 15 REFERENCES
    MLQA: Evaluating Cross-lingual Extractive Question Answering
    • 60
    • PDF
    Word Translation Without Parallel Data
    • 726
    • PDF
    Unsupervised Cross-lingual Representation Learning at Scale
    • 279
    • PDF
    75 Languages, 1 Model: Parsing Universal Dependencies Universally
    • 80
    • PDF
    CUNI Transformer Neural MT System for WMT18
    • 31
    • PDF
    DeriNet 2.0: Towards an All-in-One Word-Formation Resource
    • 7
    • Highly Influential
    • PDF
    Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition
    • 142
    • Highly Influential
    • PDF
    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
    • 11,683
    • Highly Influential
    • PDF
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,303
    • Highly Influential
    • PDF