Self-Learning Architecture for Natural Language Generation

Hyungtak Choi, Siddarth K.M., Haehun Yang, Heesik Jeon, Inchul Hwang, Jihie Kim


Abstract
In this paper, we propose a self-learning architecture for generating natural language templates for conversational assistants. Generating templates to cover all the combinations of slots in an intent is time consuming and labor-intensive. We examine three different models based on our proposed architecture - Rule-based model, Sequence-to-Sequence (Seq2Seq) model and Semantically Conditioned LSTM (SC-LSTM) model for the IoT domain - to reduce the human labor required for template generation. We demonstrate the feasibility of template generation for the IoT domain using our self-learning architecture. In both automatic and human evaluation, the self-learning architecture outperforms previous works trained with a fully human-labeled dataset. This is promising for commercial conversational assistant solutions.
Anthology ID:
W18-6520
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
165–170
Language:
URL:
https://aclanthology.org/W18-6520
DOI:
10.18653/v1/W18-6520
Bibkey:
Cite (ACL):
Hyungtak Choi, Siddarth K.M., Haehun Yang, Heesik Jeon, Inchul Hwang, and Jihie Kim. 2018. Self-Learning Architecture for Natural Language Generation. In Proceedings of the 11th International Conference on Natural Language Generation, pages 165–170, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Self-Learning Architecture for Natural Language Generation (Choi et al., INLG 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/W18-6520.pdf