Paraphrase Detection on Noisy Subtitles in Six Languages

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.

arXiv commentTo appear in Proceedings of W-NUT at EMNLP 2018, Brussels, Belgium, 1 November 2018

References in corpus (5)

• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• SentEval: An Evaluation Toolkit for Universal Sentence Representations
• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
• From Paraphrase Database to Compositional Paraphrase Model and Back
• Unsupervised Discovery of Morphemes