Question Answering over Knowledge Graphs with Neural Machine Translation and Entity Linking
–arXiv.org Artificial Intelligence
The goal of Question Answering over Knowledge Graphs (KGQA) is to find answers for natural language questions over a knowledge graph. Recent KGQA approaches adopt a neural machine translation (NMT) approach, where the natural language question is translated into a structured query language. However, NMT suffers from the out-of-vocabulary problem, where terms in a question may not have been seen during training, impeding their translation. This issue is particularly problematic for the millions of entities that large knowledge graphs describe. We rather propose a KGQA approach that delegates the processing of entities to entity linking (EL) systems. NMT is then used to create a query template with placeholders that are filled by entities identified in an EL phase. Slot filling is used to decide which entity fills which placeholder. Experiments for QA over Wikidata show that our approach outperforms pure NMT: while there remains a strong dependence on having seen similar query templates during training, errors relating to entities are greatly reduced.
arXiv.org Artificial Intelligence
Jul-6-2021
- Country:
- South America > Chile (0.04)
- Oceania
- New Zealand > North Island
- Auckland Region > Auckland (0.04)
- Australia
- Western Australia > Perth (0.04)
- Victoria > Melbourne (0.04)
- New South Wales > Sydney (0.04)
- New Zealand > North Island
- North America
- United States
- Texas > Harris County
- Houston (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- California
- Monterey County > Monterey (0.14)
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.04)
- Texas > Harris County
- Canada > Ontario
- Toronto (0.04)
- United States
- Europe
- Poland (0.14)
- Germany (0.04)
- Netherlands > North Holland
- Amsterdam (0.04)
- Austria > Styria
- Graz (0.04)
- Spain > Valencian Community
- Alicante Province > Alicante (0.04)
- Greece > Attica
- Athens (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Ireland > Connaught
- County Galway > Galway (0.04)
- France > Auvergne-Rhône-Alpes
- Asia > China
- Hong Kong (0.04)
- Genre:
- Personal > Honors (0.46)
- Research Report > New Finding (0.46)
- Technology: