Optimal Semantic Distance for Negative Example Selection in Grounded Language Acquisition
Optimal Semantic Distance for Negative Example Selection in Grounded Language Acquisition
复制标题
扎根语言习得中反例选择的最佳语义距离
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
npillai
中科院分区：
文献类型：
--
作者：
Nisha Pillai;Francis Ferraro;Cynthia Matuszek;npillai
接地的语言习得，其中话语的意义是从物理世界中学习的，通常被视为数据驱动的机器学习问题。对于机器人来说，获得语言指称的否定例子是一个具有挑战性的问题：人们倾向于描述真实的情况，而不是否定它。
Grounded language acquisition, in which the meanings of utterances are learned from and with respect to the physical world, is often treated as a data-driven machine learning problem. For a robot, obtaining negative examples of language referents is a challenging problem: people tend to describe things that are true of a situation, rather than negatives about it.
DOI：
--
发表时间：
2018
期刊：
Proceedings of the 32nd Conference on Artificial Intelligence (AAAI
影响因子：
--
作者：
Pillai, Nisha;Matuszek, Cynthia
通讯作者：
Matuszek, Cynthia