Enhancement of Subjective Content Descriptions by using Human Feedback
Magnus Bender, Tanya Braun, Ralf M\"oller, Marcel Gehrke

TL;DR
This paper introduces ReFrESH, a method that uses human feedback to improve subjective content descriptions in text retrieval systems, making answers more aligned with individual user perceptions.
Contribution
It presents a novel approach for incrementally updating subjective content descriptions using human feedback, addressing ambiguity and preserving relations among descriptions.
Findings
ReFrESH effectively updates SCDs with human feedback.
The approach improves answer relevance to user perceptions.
It manages feedback ambiguity and relation preservation.
Abstract
An agent providing an information retrieval service may work with a corpus of text documents. The documents in the corpus may contain annotations such as Subjective Content Descriptions (SCD) -- additional data associated with different sentences of the documents. Each SCD is associated with multiple sentences of the corpus and has relations among each other. The agent uses the SCDs to create its answers in response to queries supplied by users. However, the SCD the agent uses might reflect the subjective perspective of another user. Hence, answers may be considered faulty by an agent's user, because the SCDs may not exactly match the perceptions of an agent's user. A naive and very costly approach would be to ask each user to completely create all the SCD themselves. To use existing knowledge, this paper presents ReFrESH, an approach for Relation-preserving Feedback-reliant Enhancement…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Text Analysis Techniques
Methodstravel james
