Meaning and compositionality as statistical induction of categories and constraints
Meaning and compositionality as statistical induction of categories and constraints
复制标题
作为类别和约束的统计归纳的意义和组合性
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Lauren A. Schmidt
中科院分区：
文献类型：
--
作者：
Lauren A. Schmidt
单词和短语是什么意思？我们如何在给定的上下文中推断它们的含义？我们如何知道哪些单词组合在一起时具有有意义的含义，而不是毫无意义？作为语言学习者和说话者，我们可以从年轻时开始解决这些问题，但作为科学家，我们对这些过程的理解是有限的。本论文旨在使用计算方法来解决这些问题。贝叶斯建模提供了一种将类别和逻辑约束与概率推理相结合的方法，产生涉及分级类别成员资格并由概率推理结构控制的单词和短语含义。贝叶斯方法还允许进行调查，以单独识别语言用户在涉及基于含义的推理的特定情况下所带来的先验信念（例如，学习单词含义或识别形容词在给定上下文中适用于哪些对象），并识别语言用户可以从上下文中推断出什么。因此，这种方法还为研究不同的先验信念如何影响语言用户在给定情况下的推断以及先验信念如何随着时间的推移而发展提供了基础。我使用计算方法解决了以下问题：（1）人们如何从有限的证据中概括出一个词的含义？ (2) 人们如何理解和使用短语，特别是当这些短语中的某些单词依赖于上下文进行解释时？ （3）人们如何知道和学习哪些谓词和名词短语的组合可以合理地组合，哪些组合是无意义的？我展示了每个主题如何涉及类别的概率归纳，并检查每个领域中推理的限制。我还探讨了哪些约束本身是可以学习的。论文导师：Joshua Tenenbaum 职称：认知科学副教授
What do words and phrases mean? How do we infer their meaning in a given context? How do we know which sets of words have sensible meanings when combined, as opposed to being nonsense? As language learners and speakers, we can solve these problems starting at a young age, but as scientists, our understanding of these processes is limited. This thesis seeks to address these questions using a computational approach. Bayesian modeling provides a method of combining categories and logical constraints with probabilistic inference, yielding word and phrase meanings that involve graded category memberships and are governed by probabilistically inferred structures. The Bayesian approach also allows an investigation to separately identify the prior beliefs a language user brings to a particular situation involving meaning-based inference (e.g., learning a word meaning or identifying which objects an adjective applies to within a given context), and to identify what the language user can infer from the context. This approach therefore provides the foundation also for investigations of how different prior beliefs affect what a language user infers in a given situation, and how prior beliefs can develop over time. Using a computational approach, I address the following questions: (1) How do people generalize about a word’s meaning from limited evidence? (2) How do people understand and use phrases, particularly when some of the words in those phrases depend on context for interpretation? (3) How do people know and learn which combinations of predicates and noun phrases can sensibly be combined and which are nonsensical? I show how each of these topics involves the probabilistic induction of categories, and I examine the constraints on inference in each domain. I also explore which of these constraints may themselves be learned. Thesis Supervisor: Joshua Tenenbaum Title: Associate Professor of Cognitive Science
登录
查看更多内容
两岁的孩子对物体的大小了解多少？
影响因子：
4.6
作者：
Sera,MD;Troyer,D;Smith,LB
通讯作者：
Smith,LB
关于语言和思想：双语经验影响语义关联。
影响因子：
2
作者：
Ning,Siqi;Hayakawa,Sayuri;Bartolotti,James;Marian,Viorica
通讯作者：
Marian,Viorica
影响因子：
4.6
作者：
K. Ebeling;S. Gelman
通讯作者：
K. Ebeling;S. Gelman
结合分级类别：成员资格和典型性。
影响因子：
5.4
作者：
Huttenlocher,J;Hedges,LV
通讯作者：
Hedges,LV