Paraphrase Detection on Noisy Subtitles in Six Languages

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Kuvaus

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.
Alkuperäiskielienglanti
OtsikkoProceedings of the 2018 EMNLP Workshop W-NUT : The 4th Workshop on Noisy User-generated Text
ToimittajatWei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Sivumäärä10
JulkaisupaikkaStroudsburg
KustantajaAssociation for Computational Linguistics
Julkaisupäivä1 marraskuuta 2018
Sivut64-73
ISBN (elektroninen)978-1-948087-79-7
TilaJulkaistu - 1 marraskuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaWorkshop on Noisy User-generated Text - Brussels, Belgia
Kesto: 1 marraskuuta 20181 marraskuuta 2018
Konferenssinumero: 4

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet
  • 6121 Kielitieteet

Lainaa tätä

Sjöblom, E. I., Creutz, M. J. P., & Aulamo, M. J. (2018). Paraphrase Detection on Noisy Subtitles in Six Languages. teoksessa W. Xu, A. Ritter, T. Baldwin, & A. Rahimi (Toimittajat), Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text (Sivut 64-73). Stroudsburg: Association for Computational Linguistics.
Sjöblom, Eetu Ilari ; Creutz, Mathias Johan Philip ; Aulamo, Mikko Juhani. / Paraphrase Detection on Noisy Subtitles in Six Languages. Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text. Toimittaja / Wei Xu ; Alan Ritter ; Tim Baldwin ; Afshin Rahimi. Stroudsburg : Association for Computational Linguistics, 2018. Sivut 64-73
@inproceedings{5813a3ab43664ca5a12dc711ff5ed1a1,
title = "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.",
keywords = "113 Computer and information sciences, 6121 Languages",
author = "Sj{\"o}blom, {Eetu Ilari} and Creutz, {Mathias Johan Philip} and Aulamo, {Mikko Juhani}",
year = "2018",
month = "11",
day = "1",
language = "English",
pages = "64--73",
editor = "Wei Xu and Alan Ritter and Tim Baldwin and Afshin Rahimi",
booktitle = "Proceedings of the 2018 EMNLP Workshop W-NUT",
publisher = "Association for Computational Linguistics",
address = "International",

}

Sjöblom, EI, Creutz, MJP & Aulamo, MJ 2018, Paraphrase Detection on Noisy Subtitles in Six Languages. julkaisussa W Xu, A Ritter, T Baldwin & A Rahimi (toim), Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text. Association for Computational Linguistics, Stroudsburg, Sivut 64-73, Workshop on Noisy User-generated Text, Brussels, Belgia, 01/11/2018.

Paraphrase Detection on Noisy Subtitles in Six Languages. / Sjöblom, Eetu Ilari; Creutz, Mathias Johan Philip; Aulamo, Mikko Juhani.

Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text. toim. / Wei Xu; Alan Ritter; Tim Baldwin; Afshin Rahimi. Stroudsburg : Association for Computational Linguistics, 2018. s. 64-73.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

TY - GEN

T1 - Paraphrase Detection on Noisy Subtitles in Six Languages

AU - Sjöblom, Eetu Ilari

AU - Creutz, Mathias Johan Philip

AU - Aulamo, Mikko Juhani

PY - 2018/11/1

Y1 - 2018/11/1

N2 - 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.

AB - 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.

KW - 113 Computer and information sciences

KW - 6121 Languages

M3 - Conference contribution

SP - 64

EP - 73

BT - Proceedings of the 2018 EMNLP Workshop W-NUT

A2 - Xu, Wei

A2 - Ritter, Alan

A2 - Baldwin, Tim

A2 - Rahimi, Afshin

PB - Association for Computational Linguistics

CY - Stroudsburg

ER -

Sjöblom EI, Creutz MJP, Aulamo MJ. Paraphrase Detection on Noisy Subtitles in Six Languages. julkaisussa Xu W, Ritter A, Baldwin T, Rahimi A, toimittajat, Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text. Stroudsburg: Association for Computational Linguistics. 2018. s. 64-73