SALL-E: Situated Agent for Language Learning
SALL-E: Situated Agent for Language Learning
复制标题
SALL-E：语言学习的定位代理
DOI：
10.1609/aaai.v27i1.8475
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
James F. Allen
中科院分区：
文献类型：
--
作者：
Ian Perera;James F. Allen
我们描述了正在进行的研究，旨在通过将它们置于感官模型中，构建一个近乎一次性学习属性词和对象名称含义的认知可信系统。该系统从微软Kinect录制的人类演示中逐步学习，演示者可以使用不受限制的自然语言描述。通过只关注学习智能体自信的例子，忽略其他数据，我们实现了简单对象和属性的近一次学习。我们通过让系统生成所呈现对象的描述来评估系统的学习能力，包括它以前从未见过的对象，并将系统响应与收集到的人类对相同对象的描述进行比较。我们提出使用马氏距离的k近邻分类器检索对象示例的方法对应于对象的认知似是而非的表示。我们的初步结果表明，我们有望实现快速的、近乎一次性的、增量式的词义学习。
We describe ongoing research towards building a cognitively plausible system for near one-shot learning of the meanings of attribute words and object names, by grounding them in a sensory model. The system learns incrementally from human demonstrations recorded with the Microsoft Kinect, in which the demonstrator can use unrestricted natural language descriptions. We achieve near-one shot learning of simple objects and attributes by focusing solely on examples where the learning agent is confident, ignoring the rest of the data. We evaluate the system's learning ability by having it generate descriptions of presented objects, including objects it has never seen before, and comparing the system response against collected human descriptions of the same objects. We propose that our method of retrieving object examples with a k-nearest neighbor classifier using Mahalanobis distance corresponds to a cognitively plausible representation of objects. Our initial results show promise for achieving rapid, near one-shot, incremental learning of word meanings.