Question Answering over Knowledge Graphs with Neural Machine Translation and Entity Linking
This incremental improvement addresses entity recognition issues in KGQA systems, benefiting applications that rely on large knowledge graphs like Wikidata.
The paper tackles the out-of-vocabulary problem in neural machine translation for question answering over knowledge graphs by integrating entity linking to handle unseen entities, resulting in reduced entity-related errors and outperforming pure NMT approaches on Wikidata.
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.