Paraphrase Detection on Noisy Subtitles in Six Languages
Computation and Language
2018-09-24 v1
Abstract
We perform automatic paraphrase detection on subtitle data from the Opusparcus corpus comprising six European languages: German, English, Finnish, French, Russian, and Swedish. We train two types of supervised sentence embedding models: a word-averaging (WA) model and a gated recurrent averaging network (GRAN) model. We find out that GRAN outperforms WA and is more robust to noisy training data. Better results are obtained with more and noisier data than less and cleaner data. Additionally, we experiment on other datasets, without reaching the same level of performance, because of domain mismatch between training and test data.
Cite
@article{arxiv.1809.07978,
title = {Paraphrase Detection on Noisy Subtitles in Six Languages},
author = {Eetu Sjöblom and Mathias Creutz and Mikko Aulamo},
journal= {arXiv preprint arXiv:1809.07978},
year = {2018}
}
Comments
To appear in Proceedings of W-NUT at EMNLP 2018, Brussels, Belgium, 1 November 2018