Methods for natural language model training in natural language understanding (NLU) systems
Systems and methods for determining to perform an action of a query using a trained natural language model of a natural language understanding (NLU) system are disclosed herein. A text string corresponding to a prescribed action includes at least a content entity is received. A determination is made as to whether the text string corresponds to an audio input of a first group. In response to determining the text string corresponds to an audio input of a first group, a determination is made as to whether the text string includes an obsequious expression. In response to determining the text string corresponds to an audio input of a first group and in response to determining the text string includes an obsequious expression, a determination is made to perform the prescribed action. In response to determining the text string corresponds to an audio input of a first group and in response to determining the text string does not include the obsequious expression, a determination is made to not perform the prescribed action.
1. A computer-implemented method, comprising:
receiving a query;
determining whether the query comprises an obsequious expression;
wherein when the query does not comprise the obsequious expression, the method further comprises causing output of a first reply to the query; and
wherein when the query does comprise the obsequious expression, the method further comprises:
identifying a non-obsequious portion of the query;
determining the obsequious expression does not describe or correspond to the non-obsequious portion of the query; and
causing output of a second reply to the query that is different than the first reply to the query.
2. The method of claim 1 , wherein determining whether the query comprises the obsequious expression is performed based at least in part on determining whether the received query corresponds to audio input from a user that is associated with a particular group of users.
3. The method of claim 2 , wherein determining whether the received query corresponds to audio input from the user that is associated with the particular group of users is based on analyzing audio characteristics of the audio input.
4. The method of claim 2 , wherein, based at least in part on determining the received query corresponds to audio input from the user that is associated with the particular group of users and that the query does not comprise the obsequious expression, the method further comprises causing the first reply to the query to comprise an instructional message to solicit a modified query that includes one or more obsequious expressions.
5. The method of claim 4 , further comprises:
receiving the modified query with the one or more obsequious expressions; and
performing an action included in the modified query with the one or more obsequious expressions.
6. The method of claim 5 , further comprising:
determining whether the modified query with the one or more obsequious expressions was received within a predetermined time period from when the instructional message was output; and
based at least in part on determining the modified query with the one or more obsequious expressions was received within the predetermined time period from when the instructional message was output, performing the action included in the modified query.
7. The method of claim 5 , further comprising:
determining whether the modified query with the one or more obsequious expressions was received within a predetermined time period from when the instructional message was output; and
based at least in part on determining the modified query with the obsequious expression was not received within the predetermined time period from when the instructional message was output, declining to perform the action included in the modified query.
8. The method of claim 1 , wherein the non-obsequious portion of the query corresponds to a content item.
9. The method of claim 1 , wherein the received query comprises a request to perform an action, and wherein the second reply comprises a result of performing the action included in the received query.
10. The method of claim 1 , wherein the obsequious expression is a first obsequious expression, the query is a first query, and the method further comprising:
receiving a second query;
determining that the second query comprises a second obsequious expression;
identifying a non-obsequious portion of the second query;
determining the second obsequious expression does describe or correspond to the non-obsequious portion of the second query; and
outputting a third reply to the second query.
11. A computer-implemented system, comprising:
control circuitry; and
input/output circuitry configured to:
receive a query;
wherein the control circuitry is configured to:
determine whether the query comprises an obsequious expression;
wherein when the query does not comprise the obsequious expression, the control circuitry is further configured to cause output of a first reply to the query; and
wherein when the query does comprise the obsequious expression, the control circuitry is further configured to:
identify a non-obsequious portion of the query;
determine the obsequious expression does not describe or corresponds to the non-obsequious portion of the query; and
cause output of a second reply to the query that is different than the first reply to the query.
12. The system of claim 11 , wherein the control circuitry is configured to determine whether the query comprises the obsequious expression the control circuitry is further configured to, based at least in part on, determine whether the received query corresponds to audio input from a user that is associated with a particular group of users.
13. The system of claim 12 , wherein determining whether the received query corresponds to audio input from the user that is associated with the particular group of users is based on analyzing audio characteristics of the audio input.
14. The system of claim 12 , wherein the control circuitry is configured to, based at least in part on, determining the received query corresponds to audio input from the user that is associated with the particular group of users and that the query does not comprise the obsequious expression, the control circuitry is further configured to cause the first reply to the query to comprise an instructional message to solicit a modified query that includes one or more obsequious expressions.
15. The system of claim 14 , wherein the control circuitry is further configured to:
receive the modified query with the one or more obsequious expressions; and
perform an action included in the modified query with the one or more obsequious expressions.
16. The system of claim 15 , wherein the control circuitry is further configured to:
determine whether the modified query with the one or more obsequious expressions was received within a predetermined time period from when the instructional message was output; and
based at least in part on determining the modified query with the one or more obsequious expressions was received within the predetermined time period from when the instructional message was output, perform the action included in the modified query.
17. The system of claim 15 , wherein the control circuitry is further configured to:
determine whether the modified query with the one or more obsequious expressions was received within a predetermined time period from when the instructional message was output; and
based at least in part on determining the modified query with the obsequious expression was not received within the predetermined time period from when the instructional message was output, decline to perform the action included in the modified query.
18. The system of claim 11 , wherein the non-obsequious portion of the query corresponds to a content item.
19. The system of claim 11 , wherein the received query comprises a request to perform an action and wherein the second reply comprises a result of performing the action included in the received query.
20. The system of claim 11 , wherein the obsequious expression is a first obsequious expression, the query is a first query, and the control circuitry is further configured to:
receive a second query;
determine that the second query comprises a second obsequious expression;
identify a non-obsequious portion of the second query;
determine the second obsequious expression does describe or correspond to the non-obsequious portion of the second query; and
output a third reply to the second query.