@inproceedings{ihori-etal-2020-memory,
    title = "Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model",
    author = "Ihori, Mana  and
      Masumura, Ryo  and
      Makishima, Naoki  and
      Tanaka, Tomohiro  and
      Takashima, Akihiko  and
      Orihashi, Shota",
    editor = "Davis, Brian  and
      Graham, Yvette  and
      Kelleher, John  and
      Sripada, Yaji",
    booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
    month = dec,
    year = "2020",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.inlg-1.1",
    doi = "10.18653/v1/2020.inlg-1.1",
    pages = "1--6",
    abstract = "This paper presents a novel fusion method for integrating an external language model (LM) into the Transformer based sequence-to-sequence (seq2seq) model. While paired data are basically required to train the seq2seq model, the external LM can be trained with only unpaired data. Thus, it is important to leverage memorized knowledge in the external LM for building the seq2seq model, since it is hard to prepare a large amount of paired data. However, the existing fusion methods assume that the LM is integrated with recurrent neural network-based seq2seq models instead of the Transformer. Therefore, this paper proposes a fusion method that can explicitly utilize network structures in the Transformer. The proposed method, called memory attentive fusion, leverages the Transformer-style attention mechanism that repeats source-target attention in a multi-hop manner for reading the memorized knowledge in the LM. Our experiments on two text-style conversion tasks demonstrate that the proposed method performs better than conventional fusion methods.",
}