@inproceedings{wang-etal-2021-neural,
    title = "Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings",
    author = "Wang, Weixuan  and
      Peng, Wei  and
      Zhang, Meng  and
      Liu, Qun",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2021.emnlp-main.256/",
    doi = "10.18653/v1/2021.emnlp-main.256",
    pages = "3197--3202",
    abstract = "Neural Machine Translation (NMT) has shown a strong ability to utilize local context to disambiguate the meaning of words. However, it remains a challenge for NMT to leverage broader context information like topics. In this paper, we propose heterogeneous ways of embedding topic information at the sentence level into an NMT model to improve translation performance. Specifically, the topic information can be incorporated as pre-encoder topic embedding, post-encoder topic embedding, and decoder topic embedding to increase the likelihood of selecting target words from the same topic of the source sentence. Experimental results show that NMT models with the proposed topic knowledge embedding outperform the baselines on the English -{\ensuremath{>}} German and English -{\ensuremath{>}} French translation tasks."
}