Neural Paraphrase Identification of Questions with Noisy Pretraining
Computation and Language
2017-08-22 v2
Abstract
We present a solution to the problem of paraphrase identification of questions. We focus on a recent dataset of question pairs annotated with binary paraphrase labels and show that a variant of the decomposable attention model (Parikh et al., 2016) results in accurate performance on this task, while being far simpler than many competing neural architectures. Furthermore, when the model is pretrained on a noisy dataset of automatically collected question paraphrases, it obtains the best reported performance on the dataset.
Keywords
Cite
@article{arxiv.1704.04565,
title = {Neural Paraphrase Identification of Questions with Noisy Pretraining},
author = {Gaurav Singh Tomar and Thyago Duque and Oscar Täckström and Jakob Uszkoreit and Dipanjan Das},
journal= {arXiv preprint arXiv:1704.04565},
year = {2017}
}