Enhanced input for text analytics
A computer implemented method includes receiving text data, detecting auto-generated text in the received text data to identify tags in the received text to distinguish between the auto-generated text and user generated text, and providing the tagged text data to a machine learning language model.
1. A computer implemented method comprising:
receiving a data set containing text generated by a user and auto-generated text data selected by the user, the received text data including a tag distinguishing between the text generated by the user and auto generated text selected by the user in the data set;
detecting auto-generated text selected by the user based on the tag;
removing the auto-generated text from the data set to generate a training data set;
providing the training data set to a machine learning language model; and
training the machine learning language model with the training data set, using backpropagation by applying an objective function to correct synapse weights to generate a user particular language model.
2. The method of claim 1 wherein the auto-generated text is removed from the data set based on the tag.
3. The method of claim 1 wherein the tag comprises metadata associated with the auto-generated text.
4. The method of claim 1 wherein the tag comprises character delineated text of a markup language.
5. The method of claim 1 wherein the tag comprises metadata associated with the user generated text.
6. The method of claim 1 wherein the tag comprises multiple tags, each tag being associated with the auto-generated text in response to the received data set containing more text generated by the user than auto-generated text or wherein the tags are associated with the user generated text in response to the received text data containing more auto-generated text than text generated by the user.
7. The method of claim 1 wherein generating the user particular language model comprises training the machine learning language model with the user generated text data.
8. The method of claim 1 and further comprising providing the user generated text data remaining in the received data set as input to the machine learning language model that has already been trained.
9. The method of claim 1 wherein the received data set includes auto-generated text generated by a social media service in response to user selection of the auto-generated text.
10. A machine-readable storage device having instructions for execution by a processor of a machine to cause the processor to perform operations to perform a method, the operations comprising:
receiving a data set containing text generated by a user and auto-generated text data selected by the user, the received text data including a tag distinguishing between the text generated by the user and auto generated text selected by the user in the data set;
detecting auto-generated text selected by the user based on the tag;
removing the auto-generated text from the data set to generate a training data set;
providing the training data set to a machine learning language model; and
training the machine learning language model with the training data set, using backpropagation by applying an objective function to correct synapse weights to generate a user particular language model.
11. The device of claim 10 wherein the auto-generated text is removed from the data set based on the tag.
12. The device of claim 11 wherein the tag comprises metadata associated with the auto-generated text.
13. The device of claim 10 wherein the tag comprises character delineated text of a markup language.
14. The device of claim 10 wherein the tag comprises metadata associated with the user generated text.
15. The device of claim 10 wherein the tag comprises multiple tags, each tag being associated with the auto-generated text in response to the received data set containing more text generated by the user than auto-generated text or wherein the tags are associated with the user generated text in response to the received text data containing more auto-generated text than text generated by the user.
16. A device comprising:
a processor; and
a memory device coupled to the processor and having a program stored thereon for execution by the processor to perform operations comprising:
receiving a data set containing text generated by a user and auto-generated text data selected by the user, the received text data including a tag distinguishing between the text generated by the user and auto generated text selected by the user in the data set;
detecting auto-generated text selected by the user based on the tag;
removing the auto-generated text from the data set to generate a training data set;
providing the training data set to a machine learning language model; and
training the machine learning language model with the training data set, using backpropagation by applying an objective function to correct synapse weights to generate a user particular language model.
17. The device of claim 16 wherein the tag comprises multiple tags, each tag being associated with the auto-generated text in response to the received data set containing more text generated by the user than auto-generated text or wherein the tags are associated with the user generated text in response to the received text data containing more auto-generated text than text generated by the user.