Automated information retrieval system and semantic parsing
A method of information retrieval is provided. The method comprises receiving a query from a user and parsing the query in real-time as the user enters the query. The parsed query is interpreted dynamically based on a defined schema of a knowledge base, and a number of query interpretations is displayed in real-time as the user enters the query. When a selection of one of the query interpretations is received from the user information is retrieved from the knowledge base according to the selected query interpretation.
1. A computer-implement method of information retrieval, the method comprising:
using a number of processors to perform the steps of:
receiving a query from a user;
parsing the query in real-time as the user enters the query;
interpreting the parsed query dynamically based on a defined schema of a knowledge base, wherein interpreting the parsed query comprises generating a semantic tree from a parse tree according to a custom grammar, wherein the custom grammar recursively inspects word combinations and merges them into higher order primitives that are answerable using data in the knowledge base;
displaying a number of query interpretations in real-time as the user enters the query, each of the number of query interpretations comprising machine instructions that are executed by an information retrieval system to retrieve relevant information and display information that is used to clarify to the user how the query was interpreted and metadata necessary for executing a new search;
receiving a selection from the user of one of the query interpretations; and
retrieving information from the knowledge base according to the selection.
2. An information retrieval system, the system comprising:
a storage device configured to store program instructions; and
one or more processors operably connected to the storage device and configured to execute the program instructions to cause the system to:
receive a query from a user;
parse the query in real-time as the user enters the query;
interpret the parsed query dynamically based on a defined schema of a knowledge base, wherein interpreting the parsed query comprises generating a semantic tree from a parse tree according to a custom grammar, wherein the custom grammar recursively inspects word combinations and merges them into higher order primitives that are answerable using data in the knowledge base;
display a number of query interpretations in real-time as the user enters the query, each of the number of query interpretations comprising machine instructions that are executed by the information retrieval system to retrieve relevant information and display information that is used to clarify to the user how the query was interpreted and metadata necessary for executing a new search;
receive a selection from the user of one of the query interpretations; and
retrieve information from the knowledge base according to the selection.
3. A computer program product for retrieving information, the computer program product comprising:
a non-volatile computer readable storage medium having program instructions stored thereon to perform the steps of:
receiving a query from a user;
parsing the query in real-time as the user enters the query;
interpreting the parsed query dynamically based on a defined schema of a knowledge base, wherein interpreting the parsed query comprises generating a semantic tree from a parse tree according to a custom grammar, wherein the custom grammar recursively inspects word combinations and merges them into higher order primitives that are answerable using data in the knowledge base;
displaying a number of query interpretations in real-time as the user enters the query, each of the number of query interpretations comprising machine instructions that can be executed by an information retrieval system to retrieve relevant information and display information that is used to clarify to the user how the query was interpreted and metadata necessary for executing a new search;
receiving a selection from the user of one of the query interpretations; and
retrieving information from the knowledge base according to the selection.
4. The method of claim 1 , wherein the query interpretations comprise parameterized suggested searches that include filter and sorting criteria.
5. The method of claim 1 , wherein the knowledge base comprises unstructured data.
6. The method of claim 1 , wherein the knowledge base comprises structured data.
7. The method of claim 1 , further comprising:
automatically pre-processing documents in the knowledge base; and
storing document metadata in a queryable format.
8. The method of claim 1 , wherein a librarian service represents data in the knowledge base in a standardized representation according to the defined schema.
9. The method of claim 1 , wherein the defined schema comprises:
a description of entity types in the knowledge base;
a description of attributes that exist for all entity types in the knowledge base; and
a description of relationships between entities in the knowledge base.
10. The method of claim 1 , wherein each query interpretation includes machine instructions for how to retrieve information from the knowledge base.
11. The method of claim 1 , wherein interpreting the parsed query comprises performing speech tagging on the query received from the user.
12. The system of claim 2 , wherein the query interpretations comprise parameterized suggested searches that include filter and sorting criteria.
13. The system of claim 2 , wherein the knowledge base comprises unstructured data.
14. The system of claim 2 , wherein the knowledge base comprises structured data.
15. The system of claim 2 , wherein the processors further execute instructions to:
automatically pre-process documents in the knowledge base; and
store document metadata in a queryable format.
16. The system of claim 2 , wherein a librarian service represents data in the knowledge base in a standardized representation according to the defined schema.
17. The system of claim 2 , wherein the defined schema comprises:
a description of entity types in the knowledge base;
a description of attributes that exist for all entity types in the knowledge base; and
a description of relationships between entities in the knowledge base.
18. The system of claim 2 , wherein each query interpretation includes machine instructions for how to retrieve information from the knowledge base.
19. The system of claim 2 , wherein interpreting the parsed query comprises performing speech tagging on the query received from the user.
20. The computer program product of claim 3 , wherein the query interpretations comprise parameterized suggested searches that include filter and sorting criteria.
21. The computer program product of claim 3 , wherein a librarian service represents data in the knowledge base in a standardized representation according to the defined schema.
22. The method of claim 9 , wherein attributes and relationships contain metadata that describe:
machine identity;
type;
display name;
alternative names; and
popularity score.
23. The method of claim 9 , wherein the schema supports inheritance wherein child entities can be derived from parent entities.
24. The system of claim 17 , wherein attributes and relationships contain metadata that describe:
machine identity;
type;
display name;
alternative names; and
popularity score.
25. The system of claim 17 , wherein the schema supports inheritance wherein child entities can be derived from parent entities.