Entity Disambiguation

A method comprising:

• receiving data characterizing a document including a first entity;
• predicting, using a language model, a first replacement entity for the first entity;
• determining, using the first replacement entity and a knowledge base, a first candidate entity characterizing a first potential meaning of the first entity;
• comparing the first replacement entity and the first candidate entity;
• and
• providing the first potential meaning characterized by the first candidate entity as a disambiguation of the first entity.

A system comprising:

• at least one data processor;
• and
• memory storing executable instructions which, when executed by the at least one data processor, causes the at least one data processor to perform operations comprising:
• receiving data characterizing a document including a target word and a plurality of potential meanings for the target word;
• determining, using a language model, a first set of context words, the first set of context words for the target word;
• determining, using a knowledge base and the language model, a second set of context words, the second set of context words for the plurality of potential meanings of the target word;
• determining a score for each of the plurality of potential meanings by at least comparing the first set of context words and the second set of context words;
• and
• providing a potential meaning selected from the plurality of potential meanings that has a highest score as a disambiguation of the first word.