Providing answers to questions including assembling answers from multiple document segments

A computer system for searching through a database of documents for documents to generate a score for a candidate answer to an input query, the computer system comprising:

• a memory for storing data;
• and
• one or more processor units operatively connected to the memory to transmit data to and to receive data from the memory, and configured for:
• indexing the documents in the database, including
• for each of the documents, annotating spans of text in said each document that refer to entities with entity types to form entity annotations, and annotating, by the computer processor system, spans of text in said each document that refer to facts with fact types to form relation annotations,
• for each of the annotated spans of text that refers to one of the facts, linking, by the computer processor system, said one of the facts to said each annotation, and
• recording in an index, the entities, the facts, the annotations that refer to said entities, and the annotations that refer to said facts;
• receiving an input query;
• identifying a candidate answer to the input query;
• determining a set of the documents in the database using said index and theorem proving for scoring the candidate answer, including:
• identifying a logical proof of the candidate answer, the logical proof including a conclusion and a sequence of premises that logically prove the conclusion, including using the candidate answer as the conclusion of the logical proof,
• searching through a group of documents to identify a sub-group of documents of the group of documents, each document of the sub-group of documents including one or more of the premises of the logical proof, and wherein each of the premises of the logical proof is included in at least one of the documents of the sub-group of documents;
• using an iterative process, including a sequence of steps, to select, from said sub-group of documents, a set of documents that establish all the premises of the logical proof, including at each of the steps of the iterative process, selecting for said set of documents one of the documents that, of the documents of said sub-group of documents, has the largest number of the premises of the logical proof that, at the time of said each step, are not included in any of the documents in the set of documents;
• and
• using the set of documents to generate a score for the candidate answer.

An article of manufacture comprising:

• at least one tangible computer readable medium having computer readable program code logic to generate answers to questions, the computer readable program code logic, when executing, performing the following:
• indexing the documents in the database, including
• for each of the documents, annotating spans of text in said each document that refer to entities with entity types to form entity annotations, and annotating, by the computer processor system, spans of text in said each document that refer to facts with fact types to form relation annotations,
• for each of the annotated spans of text that refers to one of the facts, linking, by the computer processor system, said one of the facts to said each annotation, and
• recording in an index, the entities, the facts, the annotations that refer to said entities, and the annotations that refer to said facts;
• receiving an input query at a computer processor system;
• identifying, by the computer processor system, a candidate answer to the input query;
• determining a set of the documents in the database using said index and theorem proving for scoring the candidate answer, including:
• identifying, by the computer processor system, a logical proof of the candidate answer, the logical proof including a conclusion and a sequence of premises that logically prove the conclusion, including using the candidate answer as the conclusion of the logical proof,
• searching, by the computer processor system, through a group of documents to identify a sub-group of documents of the group of documents, each document of the sub-group of documents including one or more of the premises of the logical proof, and wherein each of the premises of the logical proof is included in at least one of the documents of the sub-group of documents;
• using, by the computer processor system, an iterative process, including a sequence of steps, to select, from said sup-group of documents, a set of documents that establish all the premises of the logical proof, including
• at each of the steps of the iterative process, selecting for said set of documents one of the documents that, of the documents of said sub-group of documents, has the largest number of the premises of the logical proof that, at the time of said each step, are not included in any of the documents in the set of documents;
• and
• using, by the computer processor system, the set of documents to generate a score for the candidate answer.