End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings
This addresses entity linking for question answering over knowledge graphs, offering an incremental improvement in efficiency.
The paper tackles the problem of entity linking and disambiguation in question answering over knowledge graphs by proposing an end-to-end neural network that uses word and knowledge graph embeddings with a gating mechanism. The result is a performance comparable to state-of-the-art methods while requiring less post-processing.
Entity linking - connecting entity mentions in a natural language utterance to knowledge graph (KG) entities is a crucial step for question answering over KGs. It is often based on measuring the string similarity between the entity label and its mention in the question. The relation referred to in the question can help to disambiguate between entities with the same label. This can be misleading if an incorrect relation has been identified in the relation linking step. However, an incorrect relation may still be semantically similar to the relation in which the correct entity forms a triple within the KG; which could be captured by the similarity of their KG embeddings. Based on this idea, we propose the first end-to-end neural network approach that employs KG as well as word embeddings to perform joint relation and entity classification of simple questions while implicitly performing entity disambiguation with the help of a novel gating mechanism. An empirical evaluation shows that the proposed approach achieves a performance comparable to state-of-the-art entity linking while requiring less post-processing.