@inproceedings{bonadiman-etal-2019-large,
    title = "Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning",
    author = "Bonadiman, Daniele  and
      Kumar, Anjishnu  and
      Mittal, Arpit",
    booktitle = "Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-5509",
    doi = "10.18653/v1/D19-5509",
    pages = "68--75",
    abstract = "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 Information Retrieval (NIR) system consisting of a neural network sentence encoder and an approximate k-Nearest Neighbour index for efficient vector retrieval. We also describe our mechanism to generate an annotated dataset for question paraphrase retrieval experiments automatically from question-answer logs via distant supervision. We show that the standard loss function in NIR, triplet loss, does not perform well with noisy labels. We propose smoothed deep metric loss (SDML) and with our experiments on two QPR datasets we show that it significantly outperforms triplet loss in the noisy label setting.",
}