Generating summary content tuned to a target characteristic using a word generation model

1. A method for generating a tuned summary using a word generation model, wherein the method includes one or more processing devices performing operations comprising:

prepending a training token to a set of ground truth text to generate training data;

receiving the training data at the word generation model;

training the word generation model using the training data, the training token, and a ground truth summary;

generating a learned subspace representation of input text and a target characteristic token associated with the input text by applying an encoder of the word generation model to the input text and the target characteristic token; and

generating, by a decoder of the word generation model, each word of a tuned summary of the input text from the learned subspace representation and from a feedback about preceding words of the tuned summary, wherein the tuned summary is tuned to target characteristics represented by the target characteristic token.

2. The method of claim 1 , wherein training the word generation model enables tuning of the tuned summary to a set of structural target characteristics, a set of content based target characteristics, a set of qualitative target characteristics, a set of linguistic target characteristics, or any combination thereof.

3. The method of claim 1 , wherein generating the tuned summary comprises generating the tuned summary in a word-by-word manner.

4. The method of claim 1 , wherein the one or more processing devices perform operations further comprising:

receiving, at the encoder, the training data;

modifying a focus of attention at an attention distribution block of the word generation model using a hyperparameter; and

training the word generation model using end-to-end training with the training data and the hyperparameter.

5. The method of claim 1 , wherein the one or more processing devices perform operations further comprising:

receiving, at the encoder, the training data;

identifying word generation model loss comprising log likelihood loss and return loss; and

training the word generation model using end-to-end training to reduce the word generation model loss.

6. The method of claim 1 , wherein the one or more processing devices perform operations further comprising:

receiving, at the decoder, a training data learned subspace representation of the training data;

identifying tunable linguistic characteristics of the word generation model; and

training the decoder using an optimum multiplicative factor to output a training tuned summary of the training data learned subspace representation based on at least one of the tunable linguistic characteristics.

7. The method of claim 1 , wherein the one or more processing devices perform operations further comprising:

increasing focus, by an attention distribution block, on portions of the input text that are relevant to the target characteristics represented by the target characteristic token prior to generating the tuned summary.

8. A computing system comprising:

means for receiving, at an encoder of a word generation model, training data;

means for identifying word generation model loss comprising log likelihood loss and return loss;

means for training the word generation model using end-to-end training to reduce the word generation model loss;

means for generating a learned subspace representation of input text and a target characteristic token associated with the input text by applying the encoder to the input text and the target characteristic token; and

means for generating, by a decoder of the word generation model, each word of a tuned summary of the input text from the learned subspace representation and from a feedback about preceding words of the tuned summary, wherein the tuned summary is tuned to target characteristics represented by the target characteristic token.

9. The computing system of claim 8 , further comprising:

means for increasing focus, by an attention distribution block, on portions of the input text that are relevant to the target characteristics represented by the target characteristic token prior to generating the tuned summary.

10. The computing system of claim 8 , wherein training the word generation model enables tuning of the tuned summary to a set of structural target characteristics, a set of content based target characteristics, a set of qualitative target characteristics, a set of linguistic target characteristics, or any combination thereof.

11. The computing system of claim 8 , further comprising:

means for prepending a training token to a set of ground truth text to generate the training data; and

means for training the word generation model using the training data, the training token, and a ground truth summary.

12. The computing system of claim 8 , further comprising:

means for modifying a focus of attention at an attention distribution block of a word generation model using a hyperparameter; and

means for training the word generation model using end-to-end training with the training data and the hyperparameter.

13. The computing system of claim 8 , further comprising:

means for receiving, at the decoder, a training data learned subspace representation of the training data;

means for identifying tunable linguistic characteristics of the word generation model; and

means for training the decoder using an optimum multiplicative factor to output a training tuned summary of the training data learned subspace representation based on at least one of the tunable linguistic characteristics.

14. A non-transitory computer-readable medium having instructions stored thereon, the instructions executable by a processing device to perform operations comprising:

receiving, at an encoder of a word generation model, training data;

modifying a focus of attention at an attention distribution block of the word generation model using a hyperparameter;

training the word generation model using end-to-end training with the training data and the hyperparameter;

generating a learned subspace representation of input text and a target characteristic token associated with the input text by applying the encoder to the input text and the target characteristic token; and

generating, by a decoder of the word generation model, each word of a tuned summary of the input text from the learned subspace representation and from a feedback about preceding words of the tuned summary, wherein the tuned summary is tuned to target characteristics represented by the target characteristic token.

15. The non-transitory computer-readable medium of claim 14 , wherein generating the tuned summary comprises generating the tuned summary in a word-by-word manner.

16. The non-transitory computer-readable medium of claim 14 , the instructions further executable by the processing device perform operations comprising:

prepending a training token to a set of ground truth text to generate the training data; and

training the word generation model using the training data, the training token, and a ground truth summary.

17. The non-transitory computer-readable medium of claim 14 , wherein training the word generation model enables tuning of the tuned summary to a set of structural target characteristics, a set of content based target characteristics, a set of qualitative target characteristics, a set of linguistic target characteristics, or any combination thereof.