arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.10000cs.CL
收藏

基于神经语言模型的语法归纳:一种不寻常的复制

Grammar Induction with Neural Language Models: An Unusual Replication

New York University(纽约大学)

Phu Mon Htut, Kyunghyun Cho, Samuel R. Bowman

摘要:

最近关于潜在树学习的大量工作尝试开发具有解析值潜在变量的神经网络模型,并在非解析任务上对它们进行训练,希望它们能发现可解释的树结构。在最近的一篇论文中,Shen et al.(2018)介绍了这样一个模型,并报告了语言建模目标任务的最新结果,以及选区解析的第一个强潜在树学习结果。在尝试重现这些结果时,我们发现了使原始结果难以信任的问题,包括调整甚至训练有效的测试集。在这里,我们试图在一个公平的实验中重现这些结果,并将其扩展到两个新的数据集。我们发现这项工作的结果是稳健的:所研究的模型的所有变体都优于所有潜在树学习基线,并且与符号语法归纳系统竞争。我们发现,这个模型代表了第一个经验的成功,潜在树学习,和神经网络语言建模值得进一步研究的语法归纳设置。

英文摘要:

A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree structure. In a recent paper, Shen et al. (2018) introduce such a model and report near-state-of-the-art results on the target task of language modeling, and the first strong latent tree learning result on constituency parsing. In an attempt to reproduce these results, we discover issues that make the original results hard to trust, including tuning and even training on what is effectively the test set. Here, we attempt to reproduce these results in a fair experiment and to extend them to two new datasets. We find that the results of this work are robust: All variants of the model under study outperform all latent tree learning baselines, and perform competitively with symbolic grammar induction systems. We find that this model represents the first empirical success for latent tree learning, and that neural network language modeling warrants further study as a setting for grammar induction.

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。

↑