Timezone: »

 
Poster
Faithful Embeddings for Knowledge Base Queries
Haitian Sun · Andrew Arnold · Tania Bedrax Weiss · Fernando Pereira · William Cohen

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #321
in Poster Session 2 »

The deductive closure of an ideal knowledge base (KB) contains exactly the logical queries that the KB can answer. However, in practice KBs are both incomplete and over-specified, failing to answer some queries that have real-world answers. \emph{Query embedding} (QE) techniques have been recently proposed where KB entities and KB queries are represented jointly in an embedding space, supporting relaxation and generalization in KB inference. However, experiments in this paper show that QE systems may disagree with deductive reasoning on answers that do not require generalization or relaxation. We address this problem with a novel QE method that is more faithful to deductive reasoning, and show that this leads to better performance on complex queries to incomplete KBs. Finally we show that inserting this new QE module into a neural question-answering system leads to substantial improvements over the state-of-the-art.

Author Information

Haitian Sun (Google Research)
Andrew Arnold (Amazon)
Tania Bedrax Weiss (Google)
Fernando Pereira (Google)
William Cohen (Google AI)

More from the Same Authors