Compound Probabilistic Context-Free Grammars for Grammar Induction
Compound Probabilistic Context-Free Grammars for Grammar Induction
复制标题
DOI：
10.18653/v1/p19-1228
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Yoon Kim;Chris Dyer;Alexander M. Rush
中科院分区：
文献类型：
--
作者：
Yoon Kim;Chris Dyer;Alexander M. Rush
我们研究了语法归纳问题的形式化，该问题将句子建模为由复合概率上下文无关语法生成。与学习单一随机语法的传统公式相比，我们的上下文无关规则概率由每个句子的连续潜在变量进行调制，这导致了超出传统上下文无关假设的边际依赖性。这种依赖于上下文的语法中的推理是通过折叠变分推理来执行的，其中摊销变分后验被放置在连续变量上，并且潜在树通过动态规划被边缘化。英语和汉语的实验表明，与最近使用神经语言模型从单词进行语法归纳的最先进方法相比，我们的方法是有效的。
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 context-free rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this context-dependent 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 with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods for grammar induction from words with neural language models.