[go: up one dir, main page]

Domainless Adaptation by Constrained Decoding on a Schema Lattice

Young-Bum Kim, Karl Stratos, Ruhi Sarikaya


Abstract
In many applications such as personal digital assistants, there is a constant need for new domains to increase the system’s coverage of user queries. A conventional approach is to learn a separate model every time a new domain is introduced. This approach is slow, inefficient, and a bottleneck for scaling to a large number of domains. In this paper, we introduce a framework that allows us to have a single model that can handle all domains: including unknown domains that may be created in the future as long as they are covered in the master schema. The key idea is to remove the need for distinguishing domains by explicitly predicting the schema of queries. Given permitted schema of a query, we perform constrained decoding on a lattice of slot sequences allowed under the schema. The proposed model achieves competitive and often superior performance over the conventional model trained separately per domain.
Anthology ID:
C16-1193
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2051–2060
Language:
URL:
https://aclanthology.org/C16-1193
DOI:
Bibkey:
Cite (ACL):
Young-Bum Kim, Karl Stratos, and Ruhi Sarikaya. 2016. Domainless Adaptation by Constrained Decoding on a Schema Lattice. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2051–2060, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Domainless Adaptation by Constrained Decoding on a Schema Lattice (Kim et al., COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1193.pdf