Dialog apparatus, dialog system, and computer-readable recording medium
AssigneeNEC Corporation
InventorTakuya HIRAOKA
Life of this patent
Estimating the term…
Abstract
A dialog apparatus 100 is an apparatus for responding to a dialog act of a user. The dialog apparatus 100 is provided with: a policy unit 40 configured to set a score to each of response candidates included in a set of response candidates based on the state of a dialog being performed with the user and a policy parameter, and referring to the set scores, to select one of the response candidates as a dialog act of the dialog apparatus 100; and a policy parameter updating unit 60 configured to obtain a reward in the state of the dialog using a reward function that, as the reward, returns an evaluation of a behavior performed in a specific circumstance as a quantitatively represented numeric value, and to update the policy parameter based on the obtained reward.
Claims12
A dialog apparatus for responding to a dialog act of a user, the dialog apparatus comprising:
- a policy unit configured to set a score to each of response candidates included in a set of response candidates based on the state of a dialog being performed with the user and a policy parameter, and referring to the set scores, to select one of the response candidates as a dialog act of the apparatus;
- and
- a policy parameter updating unit configured to obtain a reward in the state of the dialog using a reward function that, as the reward, returns an evaluation of a behavior performed in a specific circumstance as a quantitatively represented numeric value, and to update the policy parameter based on the obtained reward.
A dialog method of responding to a dialog act of a user, the dialog method comprising:
- (a) a step of setting a score to each of response candidates included in a set of response candidates based on the state of a dialog being performed with the user and a policy parameter, and referring to the set scores, selecting one of the response candidates as a dialog act;
- and
- (b) a step of obtaining a reward in the state of the dialog using a reward function that, as the reward, returns an evaluation of a behavior performed in a specific circumstance as a quantitatively represented numeric value, and updating the policy parameter based on the obtained reward.
A computer readable A non-transitory computer-readable recording medium that includes a program recorded thereon for causing a computer to respond to a dialog act of a user, the program including instructions that cause the computer to carry out:
- (a) a step of setting a score to each of response candidates included in a set of response candidates based on the state of a dialog being performed with the user and a policy parameter, and referring to the set scores, selecting one of the response candidates as a dialog act;
- and
- (b) a step of obtaining a reward in the state of the dialog using a reward function that, as the reward, returns an evaluation of a behavior performed in a specific circumstance as a quantitatively represented numeric value, and updating the policy parameter based on the obtained reward.
Dependencies are inferred from the claim text.