Term Relevance Feedback for Contextual Named Entity Retrieval
This work addresses the challenge of retrieving similar entities from free text for users in information retrieval, but it is incremental as it builds on existing CNER frameworks by adding user feedback mechanisms.
The paper tackles the problem of improving Contextual Named Entity Retrieval (CNER) by incorporating user feedback on term relevance and importance, showing that human identification of important terms outperforms automated methods and that weighting these terms further enhances retrieval performance.
We address the role of a user in Contextual Named Entity Retrieval (CNER), showing (1) that user identification of important context-bearing terms is superior to automated approaches, and (2) that further gains are possible if the user indicates the relative importance of those terms. CNER is similar in spirit to List Question answering and Entity disambiguation. However, the main focus of CNER is to obtain user feedback for constructing a profile for a class of entities on the fly and use that to retrieve entities from free text. Given a sentence, and an entity selected from that sentence, CNER aims to retrieve sentences that have entities similar to query entity. This paper explores obtaining term relevance feedback and importance weighting from humans in order to improve a CNER system. We report our findings based on the efforts of IR researchers as well as crowdsourced workers.