TY - GEN
T1 - Few shot dialogue state tracking using meta-learning
AU - Dingliwal, Saket
AU - Gao, Bill
AU - Agarwal, Sanchit
AU - Lin, Chien Wei
AU - Chung, Tagyoung
AU - Hakkani-Tür, Dilek
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models and datasets with significant (5-25%) improvement over the baseline in low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.
AB - Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models and datasets with significant (5-25%) improvement over the baseline in low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.
UR - http://www.scopus.com/inward/record.url?scp=85107269116&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107269116&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85107269116
T3 - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
SP - 1730
EP - 1739
BT - EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021
Y2 - 19 April 2021 through 23 April 2021
ER -