Paraphrase Detection on Noisy Subtitles in Six Languages

Eetu Sjöblom, Mathias Creutz, Mikko Aulamo


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.
Anthology ID:
W18-6109
Volume:
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–73
Language:
URL:
https://aclanthology.org/W18-6109
DOI:
10.18653/v1/W18-6109
Bibkey:
Cite (ACL):
Eetu Sjöblom, Mathias Creutz, and Mikko Aulamo. 2018. Paraphrase Detection on Noisy Subtitles in Six Languages. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 64–73, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Paraphrase Detection on Noisy Subtitles in Six Languages (Sjöblom et al., WNUT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6109.pdf
Data
OpenSubtitlesOpusparcusSICKSentEval