Intent matching engine
A server accesses a natural language query. The server facilitates a mapping of the natural language query to a vector using a query-to-vector engine. The server matches the vector to an intent representing a prediction associated with the natural language query. The server provides a response to the natural language query based on the intent.
1. A method, comprising:
accessing a natural language query;
facilitating a mapping of the natural language query to a vector using a query-to-vector engine;
matching, using a vector-to-intent engine, the vector to an intent representing a prediction associated with the natural language query, the vector-to-intent engine being trained by locking word embeddings and using a learning engine with a training dataset comprising a set of queries and intents matched to queries in the set; and
providing a response to the natural language query based on the intent.
2. The method of claim 1 , comprising:
testing the query-to-vector engine and the vector-to-intent engine—by verifying that a first query in a first natural language matches to a same intent as a translation of the first query into a second natural language.
3. The method of claim 1 , wherein the query-to-vector engine is configured to leverage the word embeddings in each of a plurality of natural languages to map natural language queries in the plurality of natural languages to vectors corresponding to meanings of the natural language queries.
4. The method of claim 1 , wherein the intent represents a grouping of a set of queries, including the natural language query, for further processing.
5. The method of claim 1 , wherein the vector is a numeric vector in a multi-dimensional space.
6. The method of claim 1 , wherein facilitating the mapping of the natural language query to the vector does not include translating the natural language query into a natural language different from a natural language of the natural language query.
7. The method of claim 1 , wherein the vector is matched to the intent using a machine learning technique.
8. Non-transitory computer readable media storing instructions operable to cause one or more processors to perform operations comprising:
accessing a natural language query;
facilitating a mapping of the natural language query to a vector using a query-to-vector engine;
matching, using a vector-to-intent engine, the vector to an intent representing a prediction associated with the natural language query, the vector-to-intent engine being trained by locking word embeddings and using a learning engine with a training dataset comprising a set of queries and intents matched to queries in the set; and
providing a response to the natural language query based on the intent.
9. The computer readable media of claim 8 , the operations comprising:
testing the query-to-vector engine and the vector-to-intent engine by verifying that a first query in a first natural language matches to a same intent as a translation of the first query into a second natural language.
10. The computer readable media of claim 8 , wherein the query-to-vector engine is configured to leverage the word embeddings in each of a plurality of natural languages to map natural language queries in the plurality of natural languages to vectors corresponding to meanings of the natural language queries.
11. The computer readable media of claim 8 , wherein the intent represents a grouping of a set of queries, including the natural language query, for further processing.
12. The computer readable media of claim 8 , wherein the vector is a numeric vector in a multi-dimensional space.
13. The computer readable media of claim 8 , wherein facilitating the mapping of the natural language query to the vector does not include translating the natural language query into a natural language different from a natural language of the natural language query.
14. The computer readable media of claim 8 , wherein the vector is matched to the intent using a machine learning technique.
15. A system comprising:
memory hardware; and
one or more processors configured to execute instructions stored in the memory hardware to:
access a natural language query;
facilitate a mapping of the natural language query to a vector using a query-to-vector engine;
match, using a vector-to-intent engine, the vector to an intent representing a prediction associated with the natural language query, the vector-to-intent engine being trained by locking word embeddings and using a learning engine with a training dataset comprising a set of queries and intents matched to queries in the set; and
provide a response to the natural language query based on the intent.
16. The system of claim 15 , the one or more processors configured to execute the instructions stored in the memory hardware to:
testing the query-to-vector engine and the vector-to-intent engine by verifying that a first query in a first natural language matches to a same intent as a translation of the first query into a second natural language.
17. The system of claim 15 , wherein the query-to-vector engine is configured to leverage the word embeddings in each of a plurality of natural languages to map natural language queries in the plurality of natural languages to vectors corresponding to meanings of the natural language queries.
18. The system of claim 15 , wherein the intent represents a grouping of a set of queries, including the natural language query, for further processing.
19. The system of claim 15 , wherein the vector is a numeric vector in a multi-dimensional space.
20. The system of claim 15 , wherein facilitating the mapping of the natural language query to the vector does not include translating the natural language query into a natural language different from a natural language of the natural language query.