Technical document issues scanner

A physical article of manufacture including one or more tangible computer-readable storage media, encoding computer-executable instructions for executing on a computer system a computer process comprising:

• scanning a document to extract content;
• applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
• extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
• and
• analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.

A computer-implemented method comprising:

• scanning a technical document to extract content;
• applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
• extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
• and
• analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.

A system comprising:

• one or more processor units;
• memory storing instructions that, when executed by the one or more processor units, cause the system to perform operations comprising:
• scanning a document to extract content;
• applying a named entity recognition (NER) model on the extracted content to extract named entities, the named entities comprising at least one object definition entity and at least one object reference entity;
• extracting relations between the named entities by applying a relation extraction model on the named entities to associate an object definition entity from among the named entities with a definition list and an object reference entity from among the named entities with a reference list;
• and
• analyzing the relations between the named entities by identifying a definition from the definition list for a corresponding entity in the reference list to compose lists of high relevance categories for issue checking.