Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

Bo-Hsiang Tseng, Paweł Budzianowski, Yen-chen Wu, Milica Gasic


Abstract
Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain. This is particularly the case for dialogue systems, where we want to be able to seamlessly include new domains into the conversation. Therefore, it is crucial for generation models to share knowledge across domains for the effective adaptation from one domain to another. In this study, we exploit a tree-structured semantic encoder to capture the internal structure of complex semantic representations required for multi-domain dialogues in order to facilitate knowledge sharing across domains. In addition, a layer-wise attention mechanism between the tree encoder and the decoder is adopted to further improve the model’s capability. The automatic evaluation results show that our model outperforms previous methods in terms of the BLEU score and the slot error rate, in particular when the adaptation data is limited. In subjective evaluation, human judges tend to prefer the sentences generated by our model, rating them more highly on informativeness and naturalness than other systems.
Anthology ID:
W19-5920
Volume:
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Month:
September
Year:
2019
Address:
Stockholm, Sweden
Editors:
Satoshi Nakamura, Milica Gasic, Ingrid Zukerman, Gabriel Skantze, Mikio Nakano, Alexandros Papangelis, Stefan Ultes, Koichiro Yoshino
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
155–164
Language:
URL:
https://aclanthology.org/W19-5920
DOI:
10.18653/v1/W19-5920
Bibkey:
Cite (ACL):
Bo-Hsiang Tseng, Paweł Budzianowski, Yen-chen Wu, and Milica Gasic. 2019. Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 155–164, Stockholm, Sweden. Association for Computational Linguistics.
Cite (Informal):
Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation (Tseng et al., SIGDIAL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5920.pdf