@inproceedings{tan-etal-2020-recursive,
    title = "Recursive Top-Down Production for Sentence Generation with Latent Trees",
    author = "Tan, Shawn  and
      Shen, Yikang  and
      Sordoni, Alessandro  and
      Courville, Aaron  and
      O{'}Donnell, Timothy J.",
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.findings-emnlp.208",
    doi = "10.18653/v1/2020.findings-emnlp.208",
    pages = "2291--2307",
    abstract = "We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task.",
}