Early Fusion Strategy for Entity-Relationship Retrieval
This addresses entity-relationship retrieval for complex queries, but it appears incremental as it builds on existing early fusion patterns.
The paper tackles the problem of entity-relationship retrieval by proposing an IR-centric approach based on early fusion, achieving promising results on 469 queries using Wikipedia and ClueWeb-09-B data.
We address the task of entity-relationship (E-R) retrieval, i.e, given a query characterizing types of two or more entities and relationships between them, retrieve the relevant tuples of related entities. Answering E-R queries requires gathering and joining evidence from multiple unstructured documents. In this work, we consider entity and relationships of any type, i.e, characterized by context terms instead of pre-defined types or relationships. We propose a novel IR-centric approach for E-R retrieval, that builds on the basic early fusion design pattern for object retrieval, to provide extensible entity-relationship representations, suitable for complex, multi-relationships queries. We performed experiments with Wikipedia articles as entity representations combined with relationships extracted from ClueWeb-09-B with FACC1 entity linking. We obtained promising results using 3 different query collections comprising 469 E-R queries.