@inproceedings{nehrdich-2022-sanstib,
    title = "{S}ans{T}ib, a {S}anskrit - {T}ibetan Parallel Corpus and Bilingual Sentence Embedding Model",
    author = "Nehrdich, Sebastian",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.lrec-1.724/",
    pages = "6728--6734",
    abstract = "This paper presents the development of SansTib, a Sanskrit - Classical Tibetan parallel corpus automatically aligned on sentence-level, and a bilingual sentence embedding model. The corpus has a size of about 317,289 sentence pairs and 14,420,771 tokens and thereby is a considerable improvement over previous resources for these two languages. The data is incorporated into the BuddhaNexus database to make it accessible to a larger audience. It also presents a gold evaluation dataset and assesses the quality of the automatic alignment."
}