Simple and Effective Paraphrastic Similarity from Parallel Translations

@inproceedings{Wieting2019SimpleAE,
  title={Simple and Effective Paraphrastic Similarity from Parallel Translations},
  author={J. Wieting and Kevin Gimpel and Graham Neubig and Taylor Berg-Kirkpatrick},
  booktitle={ACL},
  year={2019}
}
  • J. Wieting, Kevin Gimpel, +1 author Taylor Berg-Kirkpatrick
  • Published in ACL 2019
  • Computer Science
  • We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating para-phrase corpora. Further, we show that the resulting model can be applied to cross lingual tasks where it both outperforms and is orders of magnitude faster than more complex state-of-the-art baselines. 
    20 Citations

    Figures, Tables, and Topics from this paper

    Parallel Sentence Mining by Constrained Decoding
    • 1
    • PDF
    Simulated Multiple Reference Training Improves Low-Resource Machine Translation
    • 4
    • PDF
    A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards
    • Highly Influenced
    • PDF
    On Learning Text Style Transfer with Direct Rewards
    • PDF
    Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
    • 9
    • PDF
    Experiments on Paraphrase Identification Using Quora Question Pairs Dataset
    • 2
    • PDF
    Multilingual Alignment of Contextual Word Representations
    • 40
    • PDF
    A BILINGUAL GENERATIVE TRANSFORMER
    • 2019
    • Highly Influenced

    References

    SHOWING 1-10 OF 42 REFERENCES
    Improved Statistical Machine Translation Using Paraphrases
    • 313
    • PDF
    Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext
    • 50
    • PDF
    Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations
    • 132
    • PDF
    Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
    • 62
    • PDF
    An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification
    • 42
    • PDF
    Towards Universal Paraphrastic Sentence Embeddings
    • 414
    • PDF
    Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
    • 22
    • PDF