Automatically generating question-answer pairs during content ingestion by a question answering computing system

摘要

During ingestion of non-natural language text content into a knowledge base, a question answering computing system (QA system) converts the content into natural language text. The QA system identifies natural language sentences in the content and converts the sentences into well-formed simple sentences by resolving grammatical ambiguities in the sentences. The QA system then generates question-answer pairs (QA pairs) from the well-formed simple sentence and stores the QA pairs in a persistent store.

主权项

1. A method for automatically generating a set of question-answer pairs (QA pairs) by a question answering computing system (QA system), the QA system associated with a knowledge base, the method comprising:
initiating, by the QA system, ingestion of a content item into the knowledge base, the content item in a format, the format not a text format for a natural language; converting, by the QA system, the format of the content item to a first text format for a first natural language; identifying, by the QA system, a plurality of sentences in the first natural language in the content item; converting, by the QA system, the plurality of sentences into a plurality of simple sentences, each simple sentence in the plurality having a single subject and a single verb, at least one simple sentence in the plurality having a grammatical ambiguity; converting, by the QA system, the plurality of simple sentences into a plurality of well-formed simple sentences by resolving the grammatical ambiguity in the at least one simple sentence; generating, by the QA system, the set of QA pairs from the plurality of well-formed simple sentences; storing, by the QA system, the set of QA pairs in a persistent store; and completing, by the QA system and after the generating the set of QA pairs, the ingestion of the content item into the knowledge base.