@inproceedings{felhi-etal-2022-exploiting,
    title = "Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with {VAE}s",
    author = "Felhi, Ghazi  and
      Le Roux, Joseph  and
      Seddah, Djam{\'e}",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.naacl-main.423/",
    doi = "10.18653/v1/2022.naacl-main.423",
    pages = "5763--5776",
    abstract = "We propose a generative model for text generation, which exhibits disentangled latent representations of syntax and semantics. Contrary to previous work, this model does not need syntactic information such as constituency parses, or semantic information such as paraphrase pairs. Our model relies solely on the inductive bias found in attention-based architectures such as Transformers. In the attention of Transformers, $keys$ handle information selection while $values$ specify what information is conveyed. Our model, dubbed QKVAE, uses Attention in its decoder to read latent variables where one latent variable infers keys while another infers values. We run experiments on latent representations and experiments on syntax/semantics transfer which show that QKVAE displays clear signs of disentangled syntax and semantics. We also show that our model displays competitive syntax transfer capabilities when compared to supervised models and that comparable supervised models need a fairly large amount of data (more than 50K samples) to outperform it on both syntactic and semantic transfer. The code for our experiments is publicly available."
}