Extending monolingual semantic textual similarity task to multiple cross-lingual settings

Yoshihiko Hayashi, Wentao Luo

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    This paper describes our independent effort for extending the monolingual semantic textual similarity (STS) task setting to multiple cross-lingual settings involving English, Japanese, and Chinese. So far, we have adopted a "monolingual similarity after translation" strategy to predict the semantic similarity between a pair of sentences in different languages. With this strategy, a monolingual similarity method is applied after having (one of) the target sentences translated into a pivot language. Therefore, this paper specifically details the required and developed resources to implement this framework, while presenting our current results for English-Japanese-Chinese cross-lingual STS tasks that may exemplify the validity of the framework.

    Original languageEnglish
    Title of host publicationProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016
    PublisherEuropean Language Resources Association (ELRA)
    Pages1233-1239
    Number of pages7
    ISBN (Electronic)9782951740891
    Publication statusPublished - 2016 Jan 1
    Event10th International Conference on Language Resources and Evaluation, LREC 2016 - Portoroz, Slovenia
    Duration: 2016 May 232016 May 28

    Other

    Other10th International Conference on Language Resources and Evaluation, LREC 2016
    CountrySlovenia
    CityPortoroz
    Period16/5/2316/5/28

      Fingerprint

    Keywords

    • Cross-lingual semantic similarity
    • Machine translation quality
    • Semantic textual similarity
    • STS

    ASJC Scopus subject areas

    • Linguistics and Language
    • Library and Information Sciences
    • Language and Linguistics
    • Education

    Cite this

    Hayashi, Y., & Luo, W. (2016). Extending monolingual semantic textual similarity task to multiple cross-lingual settings. In Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016 (pp. 1233-1239). European Language Resources Association (ELRA).