Compound probabilistic context-free grammars (C-PCFGs) have recently established a new state of the art for phrase-structure grammar induction. However, due to the high time-complexity of chart-based representation and inference, it is difficult to investigate them comprehensively. In this work, we rely on a fast implementation of C-PCFGs to conduct evaluation complementary to that of~\citet{kim-etal-2019-compound}. We highlight three key findings: (1) C-PCFGs are data-efficient, (2) C-PCFGs make the best use of global sentence-level information in preterminal rule probabilities, and (3) the best configurations of C-PCFGs on English do not always generalize to morphology-rich languages.
翻译:在这项工作中,我们依靠快速实施C-PCFG来进行补充 ⁇ citet{kim-etal-2019-compuound}的评价。我们强调三个主要结论:(1)C-PCFG是数据效率高的,(2)C-PCFG在期前规则概率方面最充分地利用全球判决一级的信息,(3)C-PCFG在英语上的最佳配置并不总是概括到形式丰富的语言。