KTRL+F: Knowledge-Augmented In-Document Search

Hanseok Oh, Haebin Shin, Miyoung Ko, Hyunji Lee, Minjoon Seo


Abstract
We introduce a new problem KTRL+F, a knowledge-augmented in-document search that necessitates real-time identification of all semantic targets within a document with the awareness of external sources through a single natural query. KTRL+F addresses following unique challenges for in-document search: 1) utilizing knowledge outside the document for extended use of additional information about targets, and 2) balancing between real-time applicability with the performance.We analyze various baselines in KTRL+F and find limitations of existing models, such as hallucinations, high latency, or difficulties in leveraging external knowledge. Therefore, we propose a Knowledge-Augmented Phrase Retrieval model that shows a promising balance between speed and performance by simply augmenting external knowledge in phrase embedding. We also conduct a user study to verify whether solving KTRL+F can enhance search experience for users. It demonstrates that even with our simple model, users can reduce the time for searching with less queries and reduced extra visits to other sources for collecting evidence. We encourage the research community to work on KTRL+F to enhance more efficient in-document information access.
Anthology ID:
2024.naacl-long.134
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2416–2436
Language:
URL:
https://aclanthology.org/2024.naacl-long.134
DOI:
Bibkey:
Cite (ACL):
Hanseok Oh, Haebin Shin, Miyoung Ko, Hyunji Lee, and Minjoon Seo. 2024. KTRL+F: Knowledge-Augmented In-Document Search. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2416–2436, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
KTRL+F: Knowledge-Augmented In-Document Search (Oh et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.134.pdf
Copyright:
 2024.naacl-long.134.copyright.pdf