您现在的位置:首页> 外文会议>Annual meeting of the Society for Computation in Linguistics >文献详情

【6h】Do RNNs learn human-like abstract word order preferences?

机译RNN是否学习类似人类的抽象词序偏好?

【摘要】RNN language models have achieved state-of-the-art results on various tasks, but what exactly they are representing about syntax is as yet unclear. Here we investigate whether RNN language models learn humanlike word order preferences in syntactic alternations. We collect language model surprisal scores for controlled sentence stimuli exhibiting major syntactic alternations in English: heavy NP shift, particle shift, the dative alternation, and the genitive alternation. We show that RNN language models reproduce human preferences in these alternations based on NP length, an-imacy, and definiteness. We collect human acceptability ratings for our stimuli, in the first acceptability judgment experiment directly manipulating the predictors of syntactic alternations. We show that the RNNs' performance is similar to the human acceptability ratings and is not matched by an n-gram baseline model. Our results show that RNNs learn the abstract features of weight, animacy, and definiteness which underlie soft constraints on syntactic alternations.

【作者】Richard Futrell;Roger P. Levy;

【作者单位】Department of Language Science, UC Irvine; Department of Brain and Cognitive Sciences, MIT;

【年(卷),期】2019(),

【年度】2019

【页码】50-59

【总页数】10

【正文语种】eng

【中图分类】;

【关键词】