ITR: Bayesian Learning at the Syntax-Semantics Interface

ITR：句法语义接口的贝叶斯学习

• 批准号: 0218852
• 负责人: Robert Berwick
• 金额: $ 40万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-09-01 至 2005-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0218852&HistoricalAwards=false
• 关键词: ITR; Bayesian; Learning; Syntax; Semantics

Bayesian Learning at the Syntax-Semantics InterfaceAbstractChildren easily learn features of novel verbs from small numbers of scene-utterance pairs. For example, after encountering a few examples of "breaking" an object, they infer that break might require an object, e.g., John broke the glass. They also learn semantic properties. Children and adults can then generalize to other scene instances representing break. This project hypothesizes that children combine syntactic and semantic evidence to learn verb features, using a probabilistic method called Bayesian inference. The project's first goal is to implement a computational model that can induce probability distributions on features from a very small number of scene-utterance pairs. This model will make explicit all the information sources used. Second, the project will confirm which cues are actually used by human learners in certain settings. The experimental method matches the computer model's predictions empirically, by presenting adult and child learners with training sequences of novel verbs used across varying syntactic and semantic feature situations. This project's results will advance adaptable computer systems and information-filtering, both in terms of robustness to noise and an ability to learn from a small number of examples. These results will improve the construction of a key component of natural language processing engines: the dictionary.

贝叶斯学习在句法语义接口AbstractChildren很容易从少量的场景话语对的新动词的功能。例如，在遇到几个“破坏”对象的例子后，他们推断破坏可能需要一个对象，例如，约翰打碎了玻璃杯。他们还学习语义属性。然后，儿童和成人可以概括为其他代表中断的场景实例。 这个项目假设儿童结合联合收割机的句法和语义的证据来学习动词的特点，使用概率的方法称为贝叶斯推理。该项目的第一个目标是实现一个计算模型，该模型可以从非常少量的场景-话语对中归纳出特征的概率分布。该模型将明确所有使用的信息来源。其次，该项目将确认哪些线索实际上是由人类学习者在某些设置中使用的。实验方法匹配的计算机模型的预测经验，提出成人和儿童学习者的训练序列的新的动词在不同的句法和语义特征的情况下使用。 该项目的成果将推动适应性强的计算机系统和信息过滤，无论是在对噪声的鲁棒性方面，还是在从少量示例中学习的能力方面。这些结果将改进自然语言处理引擎的一个关键组件：词典的构建。