Interactive Dialogue Learning
PI: 蔡宗翰教授, CoPI: 李宏毅老師
計畫簡介:
本團隊以「智慧工廠」為主旨,設計一任務輔助機器人(helper bot),在使用者組裝機器人(Meccanoid2.0)的過程中給予協助,針對使用者提出之組裝問題提供操作指示。我們將組裝任務切分為多個步驟,組裝過程中透過影像辨識判斷使用者正在組裝之步驟,當使用者發問時,除了分析使用者的問句,也透過影像辨識得知使用者組裝步驟,針對該步驟可能發生之問題提出相對應解答,以期幫助使用者解決組裝難題。
Members
Publications
Y. Wang et al., "Encyclolink: A Cross-Encyclopedia, Cross-language Article-Linking System and Web-based Search Interface", in Proceedings of the IJCNLP 2017, System Demonstrations, Tapei, Taiwan: Association for Computational Linguistics, pp. 13–16.
J. Wang et al., "A Telecom-Domain Online Customer Service Assistant Based on Question Answering with Word Embedding and Intent Classification", in Proceedings of the IJCNLP 2017, System Demonstrations, Tapei, Taiwan: Association for Computational Linguistics, pp. 17–20.
T. Su, H. Lee, "Learning Chinese Word Representations From Glyphs Of Characters", in Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark: Association for Computational Linguistics, pp. 264–273.
C. Wei et al., "Personalized acoustic modeling by weakly supervised multi-task deep learning using acoustic tokens discovered from unlabeled data", in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5165-5169.
W. Ko, B. Tseng and H. Lee, "Recurrent Neural Network based language modeling with controllable external Memory", in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5705-5709.
H. Lee et al., "Personalizing Recurrent-Neural-Network-Based Language Model by Social Network", IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 3, 2017, pp. 519-530.
B. Tseng et al., "Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine", in Interspeech 2016, pp. 2731–2735.
Y. Wang, C. Wu and R. T. Tsai, "Cross-language article linking with different knowledge bases using bilingual topic model and translation features", Knowledge-Based Systems, vol. 111, 2016, pp. 228-236.