Reduced training for dialog systems using a database
Techniques are described for training and executing a machine learning model using data derived from a database. A dialog system uses data from the database to generate related training data for natural language understanding applications. The generated training data is then used to train a machine learning model. This enables the dialog system to leverage a large amount of available data to speed up the training process as compared to conventional labeling techniques. The dialog system uses the trained machine learning model to identify a named entity from a received spoken utterance and generate and output a speech response based upon the identified named entity.
1. A method comprising:
extracting data from a database, the database comprising a plurality of columns, wherein the extracted data includes a plurality of named entities extracted from a first column of the plurality of columns;
generating training data from the extracted data, the generating comprising using a named entity type corresponding to a heading associated with the first column and the extracted plurality of named entities as seed data to label each named entity of the plurality of named entities with the named entity type;
training a machine learning model using the generated training data;
receiving, by a dialog system, a spoken utterance;
identifying, by the dialog system, a named entity from the spoken utterance using the trained machine learning model;
generating, by the dialog system, a speech response based upon the identified named entity; and
providing, by the dialog system, the speech response as output.
2. The method of claim 1 , wherein generating the training data further comprises:
identifying the heading based on metadata associated with the first column of the database.
3. The method of claim 1 , wherein:
the machine learning model is a first machine learning model and the named entity is a first named entity; and
the method further comprises identifying a second named entity using a second machine learning model.
4. The method of claim 1 , wherein:
the database further comprises a plurality of requestable values; and
the method further comprises:
identifying, by the dialog system using the database, a requestable value, of the plurality of requestable values, that maps to the identified named entity,
wherein the speech response includes the requestable value or a derivative thereof.
5. The method of claim 4 , wherein:
the database comprises a plurality of tables; and
the method further comprises selecting a particular table from the plurality of tables based upon the identified named entity,
wherein the selected table is used to identify the requestable value.
6. The method of claim 5 , wherein identifying the requestable value comprises executing a query on the selected table to retrieve the requestable value mapped to the identified named entity.
7. A non-transitory computer-readable memory storing a plurality of instructions executable by one or more processors, the plurality of instructions comprising instructions that when executed by the one or more processors cause the one or more processors to perform processing comprising:
extracting data from a database, the database comprising a plurality of columns, wherein the extracted data includes a plurality of named entities extracted from a first column of the plurality of columns;
generating training data from the extracted data, the generating comprising using a named entity type corresponding to a heading associated with the first column and the extracted plurality of named entities as seed data to label each named entity of the plurality of named entities with the named entity type;
training a machine learning model using the generated training data;
receiving a spoken utterance;
identifying a named entity from the spoken utterance using the trained machine learning model;
generating a speech response based upon the identified named entity; and
providing the speech response as output.
8. The non-transitory computer-readable memory of claim 7 , wherein generating the training data further comprises:
identifying the heading based on metadata associated with the first column of the database.
9. The non-transitory computer-readable memory of claim 7 , wherein:
the machine learning model is a first machine learning model and the named entity is a first named entity; and
the processing further comprises identifying a second named entity using a second machine learning model.
10. The non-transitory computer-readable memory of claim 7 , wherein:
the database further comprises a plurality of requestable values; and
the processing further comprises:
identifying, using the database, a requestable value, of the plurality of requestable values, that maps to the identified named entity,
wherein the speech response includes the requestable value or a derivative thereof.
11. The non-transitory computer-readable memory of claim 10 , wherein:
the database comprises a plurality of tables; and
the processing further comprises selecting a particular table from the plurality of tables based upon the identified named entity,
wherein the selected table is used to identify the requestable value.
12. The non-transitory computer-readable memory of claim 11 , wherein identifying the requestable value comprises executing a query on the selected table to retrieve the requestable value mapped to the identified named entity.
13. A dialog system comprising:
one or more processors;
a memory coupled to the one or more processors, the memory storing a plurality of instructions executable by the one or more processors, the plurality of instructions comprising instructions that when executed by the one or more processors cause the one or more processors to perform processing comprising:
extracting data from a database, the database comprising a plurality of columns, wherein the extracted data includes a plurality of named entities extracted from a first column of the plurality of columns;
generating training data from the extracted data, the generating comprising using a named entity type corresponding to a heading associated with the first column and the extracted plurality of named entities as seed data to label each named entity of the plurality of named entities with the named entity type;
training a machine learning model using the generated training data;
receiving a spoken utterance;
identifying a named entity from the spoken utterance using the trained machine learning model;
generating a speech response based upon the identified named entity; and
providing the speech response as output.
14. The dialog system of claim 13 , wherein generating the training data further comprises:
identifying the heading based on metadata associated with the first column of the database.
15. The dialog system of claim 13 , wherein:
the machine learning model is a first machine learning model and the named entity is a first named entity; and
the processing further comprises identifying a second named entity using a second machine learning model.
16. The dialog system of claim 13 , wherein:
the database further comprises a plurality of requestable values; and
the processing further comprises:
identifying, using the database, a requestable value, of the plurality of requestable values, that maps to the identified named entity, wherein the speech response includes the requestable value or a derivative thereof.
17. The dialog system of claim 16 , wherein:
the database comprises a plurality of tables; and
the processing further comprises selecting a particular table from the plurality of tables based upon the identified named entity, wherein the selected table is used to identify the requestable value.