Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration

Xinmeng Li, Qian Li, Wansen Wu, Quanjun Yin


Abstract
Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains. The task is characterized by the shared slots between domains. As the scenario gets more complex, the out-of-vocabulary problem also becomes severer. Current models are not satisfactory for solving the challenges of ontology integration between domains and out-of-vocabulary problems. To address the problem, we explore the hierarchical semantic of ontology and enhance the interrelation between slots with masked hierarchical attention. In state value decoding stage, we solve the out-of-vocabulary problem by combining generation method and extraction method together. We evaluate the performance of our model on two representative datasets, MultiWOZ in English and CrossWOZ in Chinese. The results show that our model yields a significant performance gain over current state-of-the-art state tracking model and it is more robust to out-of-vocabulary problem compared with other methods.
Anthology ID:
2021.emnlp-main.171
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2241–2249
Language:
URL:
https://aclanthology.org/2021.emnlp-main.171
DOI:
10.18653/v1/2021.emnlp-main.171
Bibkey:
Cite (ACL):
Xinmeng Li, Qian Li, Wansen Wu, and Quanjun Yin. 2021. Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2241–2249, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration (Li et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2021.emnlp-main.171.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2021.emnlp-main.171.mp4
Data
CrossWOZMultiWOZ