TY - GEN
T1 - Understanding natural language sentences with word embedding and multi-modal interaction
AU - Zhong, Junpei
AU - Ogata, Tetsuya
AU - Cangelosi, Angelo
AU - Yang, Chenguang
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2018/4/2
Y1 - 2018/4/2
N2 - Understanding and grounding human commands with natural languages have been a fundamental requirement for service robotic applications. Although there have been several attempts toward this goal, the bottleneck still exists to store and process the corpora of natural language in an interaction system. Currently, the neural- and statistical-based (N&S) natural language processing have shown potential to solve this problem. With the availability of large data-sets nowadays, these processing methods are able to extract semantic relationships while parsing a corpus of natural language (NL) text without much human design, compared with the rule-based language processing methods. In this paper, we show that how two N&S based word embedding methods, called Word2vec and GloVe, can be used in natural language understanding as pre-training tools in a multi-modal environment. Together with two different multiple time-scale recurrent neural models, they form hybrid neural language understanding models for a robot manipulation experiment.
AB - Understanding and grounding human commands with natural languages have been a fundamental requirement for service robotic applications. Although there have been several attempts toward this goal, the bottleneck still exists to store and process the corpora of natural language in an interaction system. Currently, the neural- and statistical-based (N&S) natural language processing have shown potential to solve this problem. With the availability of large data-sets nowadays, these processing methods are able to extract semantic relationships while parsing a corpus of natural language (NL) text without much human design, compared with the rule-based language processing methods. In this paper, we show that how two N&S based word embedding methods, called Word2vec and GloVe, can be used in natural language understanding as pre-training tools in a multi-modal environment. Together with two different multiple time-scale recurrent neural models, they form hybrid neural language understanding models for a robot manipulation experiment.
UR - http://www.scopus.com/inward/record.url?scp=85050202520&partnerID=8YFLogxK
U2 - 10.1109/DEVLRN.2017.8329805
DO - 10.1109/DEVLRN.2017.8329805
M3 - Conference article published in proceeding or book
AN - SCOPUS:85050202520
T3 - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
SP - 184
EP - 189
BT - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
Y2 - 18 September 2017 through 21 September 2017
ER -