Regex Queries over Incomplete Knowledge Bases
This addresses the challenge of handling complex regex queries in knowledge base completion, which is incremental as it builds on existing embedding methods.
The paper tackles the problem of answering regular expression queries over incomplete knowledge bases by developing RotatE-Box, a novel combination of RotatE and box embeddings, which significantly outperforms models based on individual embeddings on new datasets.
We propose the novel task of answering regular expression queries (containing disjunction ($\vee$) and Kleene plus ($+$) operators) over incomplete KBs. The answer set of these queries potentially has a large number of entities, hence previous works for single-hop queries in KBC that model a query as a point in high-dimensional space are not as effective. In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings. It can model more relational inference patterns compared to existing embedding based models. Furthermore, we define baseline approaches for embedding based KBC models to handle regex operators. We demonstrate performance of RotatE-Box on two new regex-query datasets introduced in this paper, including one where the queries are harvested based on actual user query logs. We find that our final RotatE-Box model significantly outperforms models based on just RotatE and just box embeddings.