One model for the learning of language.
One model for the learning of language.
复制标题
DOI：
10.1073/pnas.2021865119
复制
发表时间：
2022-02-01
影响因子：
11.1
通讯作者：
Piantadosi ST
中科院分区：
文献类型：
--
作者：
Yang Y;Piantadosi ST
长期以来，人们一直假设，如果没有对自然语言结构的先天知识，语言习得可能是不可能的。在这里，我们表明，域一般的学习设置，最初开发的认知心理学模型规则学习，是能够获得关键的自然语言从相对较少的句子的例子。这为语言学习的形式化提供了一种新的方法，并突出了语言和语言习得的一些特征，这些特征可能源于一般的认知过程。语言学和认知科学的一个主要目标是了解哪类学习系统可以获得自然语言。直到最近，语言的计算要求一直被用来证明，如果没有高度约束的假设空间，学习是不可能的。在这里，我们描述了一个学习系统，它最大限度地不受约束，在所有计算的空间上运行，并且能够仅从正面证据中获取自然语言中存在的许多关键结构。我们通过提供来自74种不同形式语言的数据来证明这一点，这些语言被认为是捕捉语言的关键特征，在实验工作中进行了研究，或者来自一个有趣的复杂性类。该模型能够成功地诱导潜在系统从几乎所有情况下的少量证据生成观察到的字符串，包括对于规则（例如，an、and），上下文无关（例如，和），以及上下文敏感（例如，，和xx）语言，以及在学习实验中研究的许多语言。这些结果表明，相对少量的积极证据可以支持在结构上学习丰富的生成计算类。该模型提供了一个理想化的学习设置后，额外的认知约束和偏见可以正式。
It has long been hypothesized that language acquisition may be impossible without innate knowledge of the structures that occur in natural language. Here, we show that a domain general learning setup, originally developed in cognitive psychology to model rule learning, is able to acquire key pieces of natural language from relatively few examples of sentences. This develops a new approach to formalizing linguistic learning and highlights some features of language and language acquisition that may arise from general cognitive processes. A major goal of linguistics and cognitive science is to understand what class of learning systems can acquire natural language. Until recently, the computational requirements of language have been used to argue that learning is impossible without a highly constrained hypothesis space. Here, we describe a learning system that is maximally unconstrained, operating over the space of all computations, and is able to acquire many of the key structures present in natural language from positive evidence alone. We demonstrate this by providing the same learning model with data from 74 distinct formal languages which have been argued to capture key features of language, have been studied in experimental work, or come from an interesting complexity class. The model is able to successfully induce the latent system generating the observed strings from small amounts of evidence in almost all cases, including for regular (e.g., an, , and ), context-free (e.g., , and ), and context-sensitive (e.g., , and xx) languages, as well as for many languages studied in learning experiments. These results show that relatively small amounts of positive evidence can support learning of rich classes of generative computations over structures. The model provides an idealized learning setup upon which additional cognitive constraints and biases can be formalized.
登录
查看更多内容
影响因子：
--
作者：
BRAINE, MDS
通讯作者：
BRAINE, MDS
影响因子：
2.5
作者：
Berwick, Robert C.;Pietroski, Paul;Chomsky, Noam
通讯作者：
Chomsky, Noam
影响因子：
4.4
作者：
Aslin, Richard N.;Newport, Elissa L.
通讯作者：
Newport, Elissa L.
影响因子：
3.4
作者：
Abeille, Anne;Hemforth, Barbara;Gibson, Edward
通讯作者：
Gibson, Edward
影响因子：
5.4
作者：
BRAINE, MDS
通讯作者：
BRAINE, MDS