Cross-Domain Training for Goal-Oriented Conversational Agents

Alexandra Maria Bodîrlău, Stefania Budulan, Traian Rebedea


Abstract
Goal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large domain-specific annotated datasets. Given that the problem is closely related to the domain of the conversational agent and the data belonging to a specific domain is difficult to annotate, there have been some attempts at surpassing these challenges such as unsupervised pre-training or transfer learning between different domains. A more thorough analysis of the transfer learning mechanism is justified by the significant improvement of the results demonstrated in the results section. We describe extensive experiments using transfer learning and warm-starting techniques with improvements of more than 5% in relative percentage of success rate in the majority of cases, and up to 10x faster convergence as opposed to training the system without them.
Anthology ID:
R19-1017
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
142–150
Language:
URL:
https://aclanthology.org/R19-1017
DOI:
10.26615/978-954-452-056-4_017
Bibkey:
Cite (ACL):
Alexandra Maria Bodîrlău, Stefania Budulan, and Traian Rebedea. 2019. Cross-Domain Training for Goal-Oriented Conversational Agents. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 142–150, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Cross-Domain Training for Goal-Oriented Conversational Agents (Bodîrlău et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1017.pdf