EMNLP 2022main4 citations

Long Text Generation with Topic-aware Discrete Latent Variable Model

Erguang Yang, Mingtong Liu, Deyi Xiong, Yujie Zhang, Yufeng Chen, Jinan Xu

Abstract

Generating coherent long texts is an important yet challenging task, particularly forthe open-ended generation. Prior work based on discrete latent codes focuses on the modeling of discourse relation, resulting in discrete codes only learning shallow semantics (Ji and Huang, 2021). A natural text always revolves around several related topics and the transition across them is natural and smooth.In this work, we investigate whether discrete latent codes can learn information of topics. To this end, we build a topic-aware latent code-guided text generation model. To encourage discrete codes to model information about topics, we propose a span-level bag-of-words training objective for the model. Automatic and manual evaluation experiments show that our method can generate more topic-relevant and coherent texts.

BibTeX
@inproceedings{yang-etal-2022-long,
    title = "Long Text Generation with Topic-aware Discrete Latent Variable Model",
    author = "Yang, Erguang  and
      Liu, Mingtong  and
      Xiong, Deyi  and
      Zhang, Yujie  and
      Chen, Yufeng  and
      Xu, Jinan",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.554/",
    doi = "10.18653/v1/2022.emnlp-main.554",
    pages = "8100--8107"
}
Long Text Generation with Topic-aware Discrete Latent Variable Model · EMNLP 2022