Private Meeting Summarization Without Performance Loss
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Indsendt manuskript, 1,24 MB, PDF-dokument
Meeting summarization has an enormous business potential, but in addition to being a hard problem, roll-out is challenged by privacy concerns. We explore the problem of meeting summarization under differential privacy constraints and find, to our surprise, that while differential privacy leads to slightly lower performance on in-sample data, differential privacy improves performance when evaluated on unseen meeting types. Since meeting summarization systems will encounter a great variety of meeting types in practical employment scenarios, this observation makes safe meeting summarization seem much more feasible. We perform extensive error analysis and identify potential risks in meeting summarization under differential privacy, including a faithfulness analysis.
Originalsprog | Engelsk |
---|---|
Titel | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval |
Antal sider | 5 |
Forlag | Association for Computing Machinery, Inc. |
Publikationsdato | 2023 |
Sider | 2282-2286 |
ISBN (Elektronisk) | 9781450394086 |
DOI | |
Status | Udgivet - 2023 |
Begivenhed | 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023 - Taipei, Taiwan Varighed: 23 jul. 2023 → 27 jul. 2023 |
Konference
Konference | 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023 |
---|---|
Land | Taiwan |
By | Taipei |
Periode | 23/07/2023 → 27/07/2023 |
Sponsor | ACM SIGIR |
Bibliografisk note
Funding Information:
This work was funded by the Innovation Fund Denmark through Grand Solutions grants PIN and AutoAI4CS.
Publisher Copyright:
© 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ID: 366985696