TY - GEN
T1 - An End-to-End Dialogue Summarization System for Sales Calls
AU - Asi, Abedelkadir
AU - Wang, Song
AU - Eisenstadt, Roy
AU - Geckt, Dean
AU - Kuper, Yarin
AU - Mao, Yi
AU - Ronen, Royi
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - Summarizing sales calls is a routine task performed manually by salespeople. We present a production system which combines generative models fine-tuned for customer-agent setting, with a human-in-the-loop user experience for an interactive summary curation process. We address challenging aspects of dialogue summarization task in a real-world setting including long input dialogues, content validation, lack of labeled data and quality evaluation. We show how GPT-3 can be leveraged as an offline data labeler to handle training data scarcity and accommodate privacy constraints in an industrial setting. Experiments show significant improvements by our models in tackling the summarization and content validation tasks on public datasets.
AB - Summarizing sales calls is a routine task performed manually by salespeople. We present a production system which combines generative models fine-tuned for customer-agent setting, with a human-in-the-loop user experience for an interactive summary curation process. We address challenging aspects of dialogue summarization task in a real-world setting including long input dialogues, content validation, lack of labeled data and quality evaluation. We show how GPT-3 can be leveraged as an offline data labeler to handle training data scarcity and accommodate privacy constraints in an industrial setting. Experiments show significant improvements by our models in tackling the summarization and content validation tasks on public datasets.
UR - https://www.scopus.com/pages/publications/85137695969
U2 - 10.18653/v1/2022.naacl-industry.6
DO - 10.18653/v1/2022.naacl-industry.6
M3 - Conference contribution
AN - SCOPUS:85137695969
T3 - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Industry Papers
SP - 45
EP - 53
BT - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, NAACL 2022
Y2 - 10 July 2022 through 15 July 2022
ER -