ReFrESH – Relation-preserving Feedback-reliant Enhancement of Subjective Content Descriptions

Bender, Magnus; Braun, Tanya; Möller, Ralf; Gehrke, Marcel

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 user supplied queries. However, a user of the agent may not be the creator of the SCDs for the corpus. 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 circumvent this, this paper presents ReFrESH, an approach for Relation-preserving Feedback-reliant Enhancement of SCDs by Humans. An agent’s user can give feedback about faulty answers to the agent. This feedback is then used by ReFrESH to update the SCDs incrementally. Using ReFrESH, SCDs can be refreshed with feedback by humans and it allows users to build even better SCDs for their needs.