Semantic search with domain-specific word-embedding and production monitoring in Fintech

Mojtaba Farmanbar, Nikki Van Ommeren, Boyang Zhao


Abstract
We present an end-to-end information retrieval system with domain-specific custom language models for accurate search terms expansion. The text mining pipeline tackles several challenges faced in an industry-setting, including multi-lingual jargon-rich unstructured text and privacy compliance. Combined with a novel statistical approach for word embedding evaluations, the models can be monitored in a production setting. Our approach is used in the real world in risk management in the financial sector and has wide applicability to other domains.
Anthology ID:
2020.coling-demos.6
Volume:
Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Michal Ptaszynski, Bartosz Ziolko
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics (ICCL)
Note:
Pages:
28–33
Language:
URL:
https://aclanthology.org/2020.coling-demos.6
DOI:
10.18653/v1/2020.coling-demos.6
Bibkey:
Cite (ACL):
Mojtaba Farmanbar, Nikki Van Ommeren, and Boyang Zhao. 2020. Semantic search with domain-specific word-embedding and production monitoring in Fintech. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 28–33, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
Cite (Informal):
Semantic search with domain-specific word-embedding and production monitoring in Fintech (Farmanbar et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-demos.6.pdf