Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning

@inproceedings{Bonadiman2019LargeSQ,
  title={Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning},
  author={Daniele Bonadiman and Anjishnu Kumar and A. Mittal},
  booktitle={W-NUT@EMNLP},
  year={2019}
}
  • Daniele Bonadiman, Anjishnu Kumar, A. Mittal
  • Published in W-NUT@EMNLP 2019
  • Computer Science
  • The goal of a Question Paraphrase Retrieval (QPR) system is to retrieve equivalent questions that result in the same answer as the original question. Such a system can be used to understand and answer rare and noisy reformulations of common questions by mapping them to a set of canonical forms. This has large-scale applications for community Question Answering (cQA) and open-domain spoken language question answering systems. In this paper we describe a new QPR system implemented as a Neural… CONTINUE READING
    Experiments on Paraphrase Identification Using Quora Question Pairs Dataset

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES
    Neural Models for Information Retrieval
    106
    Efficient Large-Scale Domain Classification with Personalized Attention
    13
    Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites
    70
    Sampling Matters in Deep Embedding Learning
    305
    Attention is All you Need
    10513
    Bilateral Multi-Perspective Matching for Natural Language Sentences
    369
    Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks
    257