2026-04-30T13:12:19Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/5000 2022-03-24T23:15:04Z 1582963302567:1597824273898 user-ucsy

Robot Language Acquisition Based on Sequence-to-Sequence Learning Thu, Ye Kyaw Takabuchi, Kenta Fukai, Kaisei Iwahashi, Naoto Kunishima, Takeo Language acquisition for robot is a challenging topicin the artificial intelligence research area and essentialfor natural communication between robot and human.In this paper, we proposed language acquisition directlyfrom motion video and user’s utterance with multimodalmachine learnings without prior knowledge of linguisticor language specific information. Translation betweenacquired conceptual structure and syllable sequences ofa human language (e.g. Japanese language) was carriedout by applying machine translation methodologiesincluding sequence-to-sequence learning. Experimentson language acquisition with 500 videos show Encoder-Decoder, Encoder-Decoder with Attention models areable to achieve equal translation performance of baselinesthat was prepared manually. 2017-02-16 http://hdl.handle.net/20.500.12678/0000005000 https://meral.edu.mm/records/5000