Persian-Spanish low-resource statistical machine translation through english as pivot language

Benyamin Ahmadnia, Javier Serrano, Gholamreza Haffari

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    Abstract

    This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT). In this case, English is used as the bridging language, and the Persian-English SMT is combined with the English-Spanish one, where the relatively large corpora of each may be used in support of the Persian-Spanish pairing. Our results indicate that the pivot language technique outperforms the direct SMT processes currently in use between Persian and Spanish. Furthermore, we investigate the sentence translation pivot strategy and the phrase translation in turn, and demonstrate that, in the context of the Persian-Spanish SMT system, the phrase-level pivoting outperforms the sentence-level pivoting. Finally we suggest a method called combination model in which the standard direct model and the best triangulation pivoting model are blended in order to reach a high-quality translation.

    Original languageEnglish
    Title of host publicationInternational Conference on Recent Advances in Natural Language Processing 2017
    Subtitle of host publicationMeet Deep Learning, RANLP 2017 - Proceedings
    EditorsRuslan Mitkov , Galia Angelova
    Place of PublicationPA USA
    PublisherAssociation for Computational Linguistics (ACL)
    Pages24-30
    Number of pages7
    ISBN (Electronic)9789544520489
    DOIs
    Publication statusPublished - 2017
    EventInternational Conference on Recent Advances in Natural Language Processing 2017 - Varna, Bulgaria
    Duration: 2 Sep 20178 Sep 2017
    Conference number: 11th

    Conference

    ConferenceInternational Conference on Recent Advances in Natural Language Processing 2017
    Abbreviated titleRANLP 2017
    CountryBulgaria
    CityVarna
    Period2/09/178/09/17

    Cite this

    Ahmadnia, B., Serrano, J., & Haffari, G. (2017). Persian-Spanish low-resource statistical machine translation through english as pivot language. In R. Mitkov , & G. Angelova (Eds.), International Conference on Recent Advances in Natural Language Processing 2017: Meet Deep Learning, RANLP 2017 - Proceedings (pp. 24-30). PA USA : Association for Computational Linguistics (ACL). https://doi.org/10.26615/978-954-452-049-6-004
    Ahmadnia, Benyamin ; Serrano, Javier ; Haffari, Gholamreza. / Persian-Spanish low-resource statistical machine translation through english as pivot language. International Conference on Recent Advances in Natural Language Processing 2017: Meet Deep Learning, RANLP 2017 - Proceedings. editor / Ruslan Mitkov ; Galia Angelova . PA USA : Association for Computational Linguistics (ACL), 2017. pp. 24-30
    @inproceedings{c3a76e657369411cb8993cc80d4cd322,
    title = "Persian-Spanish low-resource statistical machine translation through english as pivot language",
    abstract = "This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT). In this case, English is used as the bridging language, and the Persian-English SMT is combined with the English-Spanish one, where the relatively large corpora of each may be used in support of the Persian-Spanish pairing. Our results indicate that the pivot language technique outperforms the direct SMT processes currently in use between Persian and Spanish. Furthermore, we investigate the sentence translation pivot strategy and the phrase translation in turn, and demonstrate that, in the context of the Persian-Spanish SMT system, the phrase-level pivoting outperforms the sentence-level pivoting. Finally we suggest a method called combination model in which the standard direct model and the best triangulation pivoting model are blended in order to reach a high-quality translation.",
    author = "Benyamin Ahmadnia and Javier Serrano and Gholamreza Haffari",
    year = "2017",
    doi = "10.26615/978-954-452-049-6-004",
    language = "English",
    pages = "24--30",
    editor = "{Mitkov }, {Ruslan } and {Angelova }, {Galia }",
    booktitle = "International Conference on Recent Advances in Natural Language Processing 2017",
    publisher = "Association for Computational Linguistics (ACL)",

    }

    Ahmadnia, B, Serrano, J & Haffari, G 2017, Persian-Spanish low-resource statistical machine translation through english as pivot language. in R Mitkov & G Angelova (eds), International Conference on Recent Advances in Natural Language Processing 2017: Meet Deep Learning, RANLP 2017 - Proceedings. Association for Computational Linguistics (ACL), PA USA , pp. 24-30, International Conference on Recent Advances in Natural Language Processing 2017, Varna, Bulgaria, 2/09/17. https://doi.org/10.26615/978-954-452-049-6-004

    Persian-Spanish low-resource statistical machine translation through english as pivot language. / Ahmadnia, Benyamin; Serrano, Javier; Haffari, Gholamreza.

    International Conference on Recent Advances in Natural Language Processing 2017: Meet Deep Learning, RANLP 2017 - Proceedings. ed. / Ruslan Mitkov ; Galia Angelova . PA USA : Association for Computational Linguistics (ACL), 2017. p. 24-30.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    TY - GEN

    T1 - Persian-Spanish low-resource statistical machine translation through english as pivot language

    AU - Ahmadnia, Benyamin

    AU - Serrano, Javier

    AU - Haffari, Gholamreza

    PY - 2017

    Y1 - 2017

    N2 - This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT). In this case, English is used as the bridging language, and the Persian-English SMT is combined with the English-Spanish one, where the relatively large corpora of each may be used in support of the Persian-Spanish pairing. Our results indicate that the pivot language technique outperforms the direct SMT processes currently in use between Persian and Spanish. Furthermore, we investigate the sentence translation pivot strategy and the phrase translation in turn, and demonstrate that, in the context of the Persian-Spanish SMT system, the phrase-level pivoting outperforms the sentence-level pivoting. Finally we suggest a method called combination model in which the standard direct model and the best triangulation pivoting model are blended in order to reach a high-quality translation.

    AB - This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT). In this case, English is used as the bridging language, and the Persian-English SMT is combined with the English-Spanish one, where the relatively large corpora of each may be used in support of the Persian-Spanish pairing. Our results indicate that the pivot language technique outperforms the direct SMT processes currently in use between Persian and Spanish. Furthermore, we investigate the sentence translation pivot strategy and the phrase translation in turn, and demonstrate that, in the context of the Persian-Spanish SMT system, the phrase-level pivoting outperforms the sentence-level pivoting. Finally we suggest a method called combination model in which the standard direct model and the best triangulation pivoting model are blended in order to reach a high-quality translation.

    UR - http://www.scopus.com/inward/record.url?scp=85045743644&partnerID=8YFLogxK

    U2 - 10.26615/978-954-452-049-6-004

    DO - 10.26615/978-954-452-049-6-004

    M3 - Conference Paper

    SP - 24

    EP - 30

    BT - International Conference on Recent Advances in Natural Language Processing 2017

    A2 - Mitkov , Ruslan

    A2 - Angelova , Galia

    PB - Association for Computational Linguistics (ACL)

    CY - PA USA

    ER -

    Ahmadnia B, Serrano J, Haffari G. Persian-Spanish low-resource statistical machine translation through english as pivot language. In Mitkov R, Angelova G, editors, International Conference on Recent Advances in Natural Language Processing 2017: Meet Deep Learning, RANLP 2017 - Proceedings. PA USA : Association for Computational Linguistics (ACL). 2017. p. 24-30 https://doi.org/10.26615/978-954-452-049-6-004