神经网络和量词保守性:数据分布影响可学习性吗?
Neural Networks and Quantifier Conservativity: Does Data Distribution Affect Learnability?
摘要:
所有已知的自然语言限定词都是保守的。心理语言学实验表明,儿童在学习新限定词时表现出相应的可学性偏向。然而,最近的工作表明,这种偏向保守性是没有观察到在人工神经网络的训练阶段。在这项工作中,我们调查是否表现出的可学性偏差的儿童是部分由于分布的量词在自然语言。我们分享了五个实验的结果,对比了训练数据中保守与非保守决定因素的分布。我们证明了非保守量词的习得问题不能用自然语言数据的分布来解释,这种分布倾向于保守量词。这一发现表明,语言习得数据中的偏见可能是先天的或表征。
英文摘要:
All known natural language determiners are conservative. Psycholinguistic experiments indicate that children exhibit a corresponding learnability bias when faced with the task of learning new determiners. However, recent work indicates that this bias towards conservativity is not observed during the training stage of artificial neural networks. In this work, we investigate whether the learnability bias exhibited by children is in part due to the distribution of quantifiers in natural language. We share results of five experiments, contrasted by the distribution of conservative vs. non-conservative determiners in the training data. We demonstrate that the aquisitional issues with non-conservative quantifiers can not be explained by the distribution of natural language data, which favors conservative quantifiers. This finding indicates that the bias in language acquisition data might be innate or representational.
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。