We study a formalization of the grammar induction problem that models
sentences as being generated by a compound probabilistic context-free grammar.
In contrast to traditional formulations which learn a single stochastic
grammar, our grammar's rule probabilities are modulated by a per-sentence
continuous latent variable, which induces marginal dependencies beyond the
traditional context-free assumptions. Inference in this grammar is performed by
collapsed variational inference, in which an amortized variational posterior is
placed on the continuous variable, and the latent trees are marginalized out
with dynamic programming. Experiments on English and Chinese show the
effectiveness of our approach compared to recent state-of-the-art methods when
evaluated on unsupervised parsing.

我们研究了一个语法归纳问题的正式化，其将句子建模为由复合概率上下文无关文法生成。与传统的学习单一随机文法的方式不同，我们的文法的规则概率由每个句子的连续潜变量调制，这在传统上下文无关假设以外引出了边际依赖性。这种文法的推理通过折叠变分推理实现，在这种方法中，连续变量上放置平化的变分后验，并通过动态规划边际化潜在树。针对英语和中文的实验表明，与最近的最先进方法相比，我们的方法在无监督语法分析评估时非常有效。