The method, system and apparatus comprise a computer program encoded on a computer storage medium capable of easily identifying entity-attribute relationships in a text corpus. The method includes determining whether an attribute in the candidate entity-attribute pair is an actual attribute of an entity in the entity-attribute candidate pair. The method may include generating embeddings for words in sentences containing entities and attributes. This step also includes generating an attribute distribution embedding for the entity based on other attributes associated with the entity and generating an attribute distribution embedding for the attribute based on the known attributes associated with the known entities of the attribute. I can. Based on this embedding, the feed forward network can determine whether an attribute in the entity-attribute candidate pair is an actual attribute of an entity in the entity-attribute candidate pair.
展开▼