Name
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.
|
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3366423.3380197 | WWW '20: The Web Conference 2020
Taipei
Taiwan
April, 2020 |
Keywords | DocType | ISBN |
Free-Text Knowledge Graph, Factoid Question Answering, Graph Neural Network | Conference | 978-1-4503-7023-3 |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen Zhao | 1 | 14 | 4.36 |
| Chen-Yan Xiong | 2 | 405 | 30.82 |
| Xin Qian | 3 | 6 | 0.88 |
| Jordan L. Boyd-Graber | 4 | 66 | 8.40 |