论文标题
关于监督在无监督的选区解析中的作用
On the Role of Supervision in Unsupervised Constituency Parsing
论文作者
论文摘要
我们分析了最近的几个无监督的选区解析模型，这些模型在《华尔街日报》（WSJ）开发集（1,700个句子）上的解析$ f_1 $得分方面进行了调整。我们通过培训现有的监督解析模型（Kitaev and Klein，2018），以与他们访问的示例相同的示例来为他们介绍强大的基线。当对1,700个示例进行培训，甚至仅使用50个示例进行培训和5个示例进行开发时，这种几次解析方法也可以大大优于所有无监督解析方法。通过简单的数据增强方法和自我训练，几乎没有射击可以进一步改善。这表明，为了得出公平的结论，我们应该仔细考虑用于模型开发的标记数据量。我们提出了两项关于无监督解析的未来工作的协议：（i）使用完全无监督的标准进行超参数调整和模型选择； （ii）使用尽可能少的标记示例进行模型开发，并与在同一标记的示例上训练的几个射击分析。
We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing $F_1$ score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.
