AKBC 2021
  • Papers
  • Speakers
  • Workshops
  • Home
  • Day 2
  • Day 2 Posters
  • Paper 59

Regex Queries over Incomplete Knowledge Bases

Vaibhav Adlakha, Parth Shah, Srikanta J. Bedathur, Mausam .

Keywords: regex, regular expressions, kleene, plus, disjunction, box embeddings, knowledge base completion

TLDR: We present Regex Query Answering, the novel task of answering regex queries on incomplete KBs

, -

Poster Session Abstract AKBC OpenReview PDF
Abstract: 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 the 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 models significantly outperform models based on just Rotate and just box embeddings.

Open Slides (in new window)

Back to Top

© 2021 AKBC Organization Committee