Complex Factoid Question Answering with a Free-Text Knowledge Graph

TL;DR

DELFT is a question answering system that constructs a free-text knowledge graph from Wikipedia and uses a graph neural network to reason over it, achieving superior performance on entity-rich questions.

Contribution

It introduces a novel free-text knowledge graph from Wikipedia and a graph neural network for reasoning, improving answer accuracy over existing models.

Findings

DELFT outperforms machine reading and bert-based models on three datasets.

The free-text knowledge graph has more than double the coverage of dbpedia relations.

The graph neural network effectively reasons over noisy free-text evidence.

Abstract

We introduce DELFT, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. DELFT builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which entities co-occur as edges. For each question, DELFT finds the subgraph linking question entity nodes to candidates using text sentences as edges, creating a dense and high coverage semantic graph. A novel graph neural network reasons over the free-text graph-combining evidence on the nodes via information along edge sentences-to select a final answer. Experiments on three question answering datasets show DELFT can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. DELFT's advantage comes from both the high coverage of its free-text knowledge graph-more than double that of dbpedia relations-and the novel graph neural network which reasons on the rich but noisy free-text evidence.