TY - GEN
T1 - Dynamic multi-level attention models for dialogue response generation
AU - Wang, Yanmeng
AU - Rong, Wenge
AU - Zhou, Shijie
AU - Ouyang, Yuanxin
AU - Xiong, Zhang
N1 - Publisher Copyright:
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.
PY - 2021
Y1 - 2021
N2 - One of the key challenges for creating a successful chat bot is to find an effective way to learn from human-human conversation data. Recently, a few neural network based dialog models, including the RNN language model (RNNLM) and the hierarchical recurrent encoder-decoder (HRED) model have shown promising results on dialog response generation. However, there is a critical challenge that the responses generated by these models incline to chit-chat style instead of being informative. In this paper, we empirically investigate this problem and also propose multilevel attention models to extend HRED with a hope that the attention mechanism can capture more informative content. The experiment studies on two multi-turn dialogue Datasets have shown the model’s potential.
AB - One of the key challenges for creating a successful chat bot is to find an effective way to learn from human-human conversation data. Recently, a few neural network based dialog models, including the RNN language model (RNNLM) and the hierarchical recurrent encoder-decoder (HRED) model have shown promising results on dialog response generation. However, there is a critical challenge that the responses generated by these models incline to chit-chat style instead of being informative. In this paper, we empirically investigate this problem and also propose multilevel attention models to extend HRED with a hope that the attention mechanism can capture more informative content. The experiment studies on two multi-turn dialogue Datasets have shown the model’s potential.
KW - Dialog generation
KW - Encoder-decoder
KW - Multi-level attention
UR - https://www.scopus.com/pages/publications/85089617770
U2 - 10.1007/978-3-030-53829-3_6
DO - 10.1007/978-3-030-53829-3_6
M3 - 会议稿件
AN - SCOPUS:85089617770
SN - 9783030538286
T3 - Advances in Intelligent Systems and Computing
SP - 62
EP - 71
BT - Distributed Computing and Artificial Intelligence, Special Sessions, 17th International Conference, DCAI 2020
A2 - Rodríguez González, Sara
A2 - Prieto, Javier
A2 - González-Briones, Alfonso
A2 - Gola, Arkadiusz
A2 - Katranas, George
A2 - Ricca, Michela
A2 - Loukanova, Roussanka
A2 - Loukanova, Roussanka
PB - Springer
T2 - 17th International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2020
Y2 - 17 June 2020 through 19 June 2020
ER -