Scaling dense PCFGs to thousands of nonterminals via a low-rank parameterization of the rule probability tensor has been shown to be beneficial for unsupervised parsing. However, PCFGs scaled this way still perform poorly as a language model, and even underperform similarly-sized HMMs. This work introduces \emph{SimplePCFG}, a simple PCFG formalism with independent left and right productions. Despite imposing a stronger independence assumption than the low-rank approach, we find that this formalism scales more effectively both as a language model and as an unsupervised parser. As an unsupervised parser, our simple PCFG obtains an average F1 of 65.1 on the English PTB, and as a language model, it obtains a perplexity of 119.0, outperforming similarly-sized low-rank PCFGs. We further introduce \emph{FlashInside}, a hardware IO-aware implementation of the inside algorithm for efficiently scaling simple PCFGs.

翻译：通过采用规则概率张量的低秩参数化方法，将稠密PCFG扩展至数千个非终结符已被证明有利于无监督句法分析。然而，以这种方式扩展的PCFG作为语言模型时仍表现不佳，甚至不如规模相当的HMM。本文提出\texttt{SimplePCFG}——一种具有独立左右生成式的简易PCFG形式体系。尽管相比低秩方法施加了更强的独立性假设，我们发现该形式体系在作为语言模型和无监督句法分析器时均能更有效地扩展。作为无监督句法分析器，我们的简易PCFG在英文PTB上平均F1值达到65.1；作为语言模型，其困惑度达到119.0，优于规模相当的低秩PCFG。我们进一步提出\texttt{FlashInside}——一种面向硬件IO感知的inside算法实现，用于高效扩展简易PCFG。