Timezone: »

LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
Hongyu Ren · Hanjun Dai · Bo Dai · Xinyun Chen · Michihiro Yasunaga · Haitian Sun · Dale Schuurmans · Jure Leskovec · Denny Zhou

Wed Jul 21 07:40 PM -- 07:45 PM (PDT) @ None

Answering complex natural language questions on knowledge graphs (KGQA) is a challenging task. It requires reasoning with the input natural language questions as well as a massive, incomplete heterogeneous KG. Prior methods obtain an abstract structured query graph/tree from the input question and traverse the KG for answers following the query tree. However, they inherently cannot deal with missing links in the KG. Here we present LEGO, a Latent Execution-Guided reasOning framework to handle this challenge in KGQA. LEGO works in an iterative way, which alternates between (1) a Query Synthesizer, which synthesizes a reasoning action and grows the query tree step-by-step, and (2) a Latent Space Executor that executes the reasoning action in the latent embedding space to combat against the missing information in KG. To learn the synthesizer without step-wise supervision, we design a generic latent execution guided bottom-up search procedure to find good execution traces efficiently in the vast query space. Experimental results on several KGQA benchmarks demonstrate the effectiveness of our framework compared with previous state of the art.

Author Information

Hongyu Ren (Stanford University)
Hanjun Dai (Google Brain)
Bo Dai (Google Brain)
Xinyun Chen (UC Berkeley)
Michihiro Yasunaga (Stanford University)
Haitian Sun (Google)
Dale Schuurmans (Google / University of Alberta)
Jure Leskovec (Stanford University)
Denny Zhou (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors