@inproceedings{zhang-etal-2020-2019,
    title = "The 2019 {BBN} Cross-lingual Information Retrieval System",
    author = "Zhang, Le  and
      Karakos, Damianos  and
      Hartmann, William  and
      Srivastava, Manaj  and
      Tarlin, Lee  and
      Akodes, David  and
      Gouda, Sanjay Krishna  and
      Bathool, Numra  and
      Zhao, Lingjun  and
      Jiang, Zhuolin  and
      Schwartz, Richard  and
      Makhoul, John",
    editor = "McKeown, Kathy  and
      Oard, Douglas W.  and
      {Elizabeth}  and
      Schwartz, Richard",
    booktitle = "Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.clssts-1.8",
    pages = "44--51",
    abstract = "In this paper, we describe a cross-lingual information retrieval (CLIR) system that, given a query in English, and a set of audio and text documents in a foreign language, can return a scored list of relevant documents, and present findings in a summary form in English. Foreign audio documents are first transcribed by a state-of-the-art pretrained multilingual speech recognition model that is finetuned to the target language. For text documents, we use multiple multilingual neural machine translation (MT) models to achieve good translation results, especially for low/medium resource languages. The processed documents and queries are then scored using a probabilistic CLIR model that makes use of the probability of translation from GIZA translation tables and scores from a Neural Network Lexical Translation Model (NNLTM). Additionally, advanced score normalization, combination, and thresholding schemes are employed to maximize the Average Query Weighted Value (AQWV) scores. The CLIR output, together with multiple translation renderings, are selected and translated into English snippets via a summarization model. Our turnkey system is language agnostic and can be quickly trained for a new low-resource language in few days.",
    language = "English",
    ISBN = "979-10-95546-55-9",
}