@inproceedings{soulos-etal-2021-structural,
    title = "Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages",
    author = "Soulos, Paul  and
      Rao, Sudha  and
      Smith, Caitlin  and
      Rosen, Eric  and
      Celikyilmaz, Asli  and
      McCoy, R. Thomas  and
      Jiang, Yichen  and
      Haley, Coleman  and
      Fernandez, Roland  and
      Palangi, Hamid  and
      Gao, Jianfeng  and
      Smolensky, Paul",
    booktitle = "Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)",
    month = aug,
    year = "2021",
    address = "Virtual",
    publisher = "Association for Machine Translation in the Americas",
    url = "https://aclanthology.org/2021.mtsummit-loresmt.6",
    pages = "52--67",
    abstract = "Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.",
}