arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.02423cs.CL
收藏

论监督在无监督选区分析中的作用

On the Role of Supervision in Unsupervised Constituency Parsing

Toyota Technological Institute at Chicago(芝加哥丰田理工学院)

Haoyue Shi, Karen Livescu, Kevin Gimpel

摘要:

我们分析了几个最近的无监督选区解析模型,这是调整相对于华尔街日报(WSJ)开发集(1,700句)的解析$F_1$分数。我们为它们引入了强大的基线,通过在它们访问的相同标记示例上训练现有的监督解析模型(Kitaev和Klein,2018)。当在1,700个示例上进行训练时,或者甚至当仅使用50个示例进行训练和5个示例进行开发时,这种Few-Shot解析方法可以显著优于所有无监督解析方法。Few-Shot解析可以通过简单的数据增强方法和自训练来进一步改进。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的数量。我们提出了两个协议,为未来的工作无监督解析:(i)使用完全无监督的超参数调整和模型选择的标准;(ii)使用尽可能少的标记的例子模型开发,并比较Few-Shot解析训练相同的标记的例子。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑