权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Acquisition of Word-meaning and Dialogue Strategies Aiming at the Communication in a Symbiotic Society of Human and Agents

人与智能体共生社会中沟通的词义习得和对话策略

基本信息

批准号：
18500130
负责人：
NITTA Tsuneo
金额：
$ 2.59万
依托单位：
Toyohashi University of Technology
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
2006
资助国家：
日本
起止时间：
2006 至 2007
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-18500130/
关键词：
Symbiosis of human and agents Communication Dialogue strategies Word meaning acquisition Learning biases Reinforcement learning 相互排他性バイアス形状類似バイアス

项目摘要

The symbiotic society of human and agents that enables them real interaction in the near future is expected. To accelerate related studies, facilities of spoken dialogue interaction and development tools are very important. We have studied first: (a) word-meaning acquisition of image objects, (b) dialogue strategy acquisition for the agents.In the word-meaning acquisition, we propose a method based on an Online-EM algorithm that enables agents to find out the features of objects represented by spoken words, however, the algorithm needs a lot of examples to determine the word-meaning, or correct distributions. To overcome the problem, we have applied two types of learning biases, shape bias and mutual exclusivity bias, observed in children's language development. Experimental results showed that the improved method with biases could efficiently acquire word meanings.In the dialogue strategy acquisition, we propose a Q-learning based algorithm in which agents acquire different strategies according with their roles, asking or teaching, by estimating counterpart's comprehension level from its facial expression and utterance. Experimental results showed the effectiveness of both strategies of teaching and asking. We have also developed a tool with the abovementioned functionalities of word-meaning acquisition and dialogue strategy acquisition. The experimental results on cooperative works showed the effectiveness of acquired action strategies to complete tasks quickly.

人类与智能体的共生社会有望在不久的将来实现真正的互动。为了加速相关研究，口语对话交互设施和开发工具非常重要。我们首先研究了：（a）图像对象的词义获取，（b）代理的对话策略获取。在词义获取中，我们提出了一种基于Online-EM算法的方法，使代理能够找出口语词所代表的对象的特征，然而，该算法需要大量的例子来确定词义或正确的分布。为了克服这个问题，我们应用了在儿童语言发展中观察到的两种学习偏差：形状偏差和互斥偏差。实验结果表明，带有偏差的改进方法可以有效地获取单词含义。在对话策略获取中，我们提出了一种基于Q-learning的算法，其中代理根据其角色、提问或教学，通过从面部表情和话语估计对方的理解水平来获取不同的策略。实验结果表明了教学和提问两种策略的有效性。我们还开发了具有上述词义获取和对话策略获取功能的工具。合作工作的实验结果表明了习得的行动策略对于快速完成任务的有效性。

项目成果

期刊论文数量（0）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Effecient Learning of Word Meanings by Agents Using Biases Observed in Language Development of Children (In Japanese)

利用儿童语言发展中观察到的偏差，智能体有效学习单词含义（日语）

DOI：
发表时间：
2007
期刊：
Transactions of the Japanese Society for Artificial Intelligence Vol. 22, No. 4
影响因子：
0
作者：
Ryo Taguchi;Masashi Kimura;Satoshi Kodama;Shuji Shinohara;Yurie Iribe;Kouichi Katsurada;Tsuneo Nitta
通讯作者：
Tsuneo Nitta

A Method for Keyword Extraction Using Retrieval Information from Students in Lectures (In Japanese)

一种利用学生讲座信息提取关键词的方法（日文）

DOI：
发表时间：
2007
期刊：
Transactions of the Japanese Society for Artificial Intelligence Vol. 22, No. 6
影响因子：
0
作者：
Shuji Shinohara;Yurie Iribe;Hiroaki Kawashima;Kouichi Katsurada;Tsuneo Nitta
通讯作者：
Tsuneo Nitta

On Autonomous Coordination of Learning Biases by an Agent with a Vocabulary Learning Mechanism (In Japanese)

具有词汇学习机制的智能体对学习偏差的自主协调（日语）

DOI：
发表时间：
2007
期刊：
Transactions of the Japanese Society for Artificial Intelligence Vol. 22, No. 2
影响因子：
0
作者：
Shuji Shinohara;Ryo Taguchi;Takashi Hashimoto;Kouichi Katsurada;Tsuneo Nitta
通讯作者：
Tsuneo Nitta

幼児エージェントにおけるバイアスの形成と言語の構造化

婴儿代理的偏见形成和语言结构