Statistically based chunking of nonadjacent dependencies.
Statistically based chunking of nonadjacent dependencies.
复制标题
DOI：
10.1037/xge0001207
复制
发表时间：
2022-11
影响因子：
4.1
通讯作者：
Christiansen, Morten H.
中科院分区：
文献类型：
--
作者：
Isbilen, Erin S.;Frost, Rebecca L. A.;Monaghan, Padraic;Christiansen, Morten H.
个体如何在环境中学习复杂的规律并将其推广到新的实例是认知科学中的一个关键问题。尽管先前的研究主张学习和泛化依赖于不同的过程，但相同的基本学习机制可能解释了两者。在语言学习实验中，这些机制通常是在与更广泛的认知现象（如记忆、感知和注意力）分离的情况下进行研究的。在这里，我们通过测试学习者对非相邻依赖项的划分能力来展示语言的学习和概括是如何嵌入到这些更广泛的理论中的。非相邻依赖项是语言的一个关键结构，但对通过记忆结构来学习的理论提出了挑战。在两项研究中，成年参与者接受了包含非相邻音节依赖的人工语言的训练和测试，使用了一种新的基于分块的连续回忆任务，包括对目标序列（由学习过的字符串组成）和打乱的箔片进行口头重复。参与者从符合语言统计的序列（包括习得序列和广义序列）中回忆出明显更多的音节、双字母、三字母和非相邻依赖。它们还对特定的非相邻块信息进行编码和泛化。这些结果表明，参与者对远程依赖进行分组，并迅速将这些信息概括为新的结构。因此，研究结果进一步支持了基于学习的语言习得方法，并将统计学习与更广泛的记忆认知机制联系起来。
How individuals learn complex regularities in the environment and generalize them to new instances is a key question in cognitive science. Although previous investigations have advocated the idea that learning and generalizing depend upon separate processes, the same basic learning mechanisms may account for both. In language learning experiments, these mechanisms have typically been studied in isolation of broader cognitive phenomena such as memory, perception, and attention. Here, we show how learning and generalization in language is embedded in these broader theories by testing learners on their ability to chunk nonadjacent dependencies—a key structure in language but a challenge to theories that posit learning through the memorization of structure. In two studies, adult participants were trained and tested on an artificial language containing nonadjacent syllable dependencies, using a novel chunking-based serial recall task involving verbal repetition of target sequences (formed from learned strings) and scrambled foils. Participants recalled significantly more syllables, bigrams, trigrams, and nonadjacent dependencies from sequences conforming to the language’s statistics (both learned and generalized sequences). They also encoded and generalized specific nonadjacent chunk information. These results suggest that participants chunk remote dependencies and rapidly generalize this information to novel structures. The results thus provide further support for learning-based approaches to language acquisition, and link statistical learning to broader cognitive mechanisms of memory.
登录
查看更多内容
影响因子：
7.2
作者：
Aslin RN;Newport EL
通讯作者：
Newport EL
影响因子：
5.4
作者：
Cowan, Nelson;Rouder, Jeffrey N.;Blume, Christopher L.;Saults, J. Scott
通讯作者：
Saults, J. Scott
DOI：
10.1080/17470210802453977
发表时间：
2009-07
期刊：
Quarterly journal of experimental psychology (2006)
影响因子：
--
作者：
Chen Z;Cowan N
通讯作者：
Cowan N
影响因子：
4.3
作者：
Endress, Ansgar D.;Mehler, Jacques
通讯作者：
Mehler, Jacques
影响因子：
4.1
作者：
Brady, Timothy F.;Konkle, Talia;Alvarez, George A.
通讯作者：
Alvarez, George A.