Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
This addresses a practical gap for users needing to query knowledge graphs with flexible preferences, though it is incremental as it builds on existing query answering methods.
The paper tackles the problem of answering queries on incomplete knowledge graphs with vague or context-dependent constraints, introducing a Neural Query Reranker (NQR) that adjusts answer scores interactively based on examples, and experiments show it captures soft constraints while maintaining robust performance.
Methods for query answering over incomplete knowledge graphs retrieve entities that are likely to be answers, which is particularly useful when such answers cannot be reached by direct graph traversal due to missing edges. However, existing approaches have focused on queries formalized using first-order-logic. In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories. Addressing this gap, we introduce the problem of query answering with soft constraints. We propose a Neural Query Reranker (NQR) designed to adjust query answer scores by incorporating soft constraints without disrupting the original answers to a query. NQR operates interactively, refining answers based on incremental examples of preferred and non-preferred entities. We extend existing QA benchmarks by generating datasets with soft constraints. Our experiments demonstrate that NQR can capture soft constraints while maintaining robust query answering performance.