An effective context-focused hierarchical mechanism for task-oriented dialogue response generation
Zhao, M., Wang, L., Jiang, Z., Li, R., Lu, X., Hu, Z. and Chen, D. (2022). An effective context-focused hierarchical mechanism for task-oriented dialogue response generation. Computational Intelligence. 38 (5), pp. 1831-1858. https://doi.org/10.1111/coin.12544
|Authors||Zhao, M., Wang, L., Jiang, Z., Li, R., Lu, X., Hu, Z. and Chen, D.|
Task-oriented dialogue system (TOD) is one kind of application of artificial intelligence (AI). The response generation module is a key component of TOD for replying to user's questions and concerns in sequential natural words. In the past few years, the works on response generation have attracted increasing research attention and have seen much progress. However, existing works ignore the fact that not each turn of dialogue history contributes to the dialogue response generation and give little consideration to the different weights of utterances in a dialogue history. In this paper, we propose a hierarchical memory network mechanism with two steps to filter out unnecessary information of dialogue history. First, an utterance-level memory network distributes various weights to each utterance (coarse-grained). Second, a token-level memory network assigns higher weights to keywords based on the former's output (fine-grained). Furthermore, the output of the token-level memory network will be employed to query the knowledge base (KB) to capture the dialogue-related information. In the decoding stage, we take a gated-mechanism to generate response word by word from dialogue history, vocabulary, or KB. Experiments show that the proposed model achieves superior results compared with state-of-the-art models on several public datasets. Further analysis demonstrates the effectiveness of the proposed method and the robustness of the model in the case of an incomplete training set.
|Keywords||task-oriented dialogue systems; memory networks; natural language generations; natural language processing (NLP); deep learning|
|Journal citation||38 (5), pp. 1831-1858|
|Digital Object Identifier (DOI)||https://doi.org/10.1111/coin.12544|
|26 Jul 2022|
|Publication process dates|
|Accepted||30 Jun 2022|
|Deposited||30 Jun 2022|
|Accepted author manuscript|
File Access Level
This is the peer reviewed version of the following article: An effective context-focused hierarchical mechanism for task-oriented dialogue response generation, which has been published in final form at https://onlinelibrary.wiley.com/doi/full/10.1111/coin.12544. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited.
0views this month
0downloads this month