Autonomous webpage content summation

1. A method, comprising:

receiving, by a computing device, text extracted from a webpage in a browser and a Uniform Resource Locator (URL) of a linked webpage associated with the text;

generating, by the computing device, questions based on the text;

retrieving, by the computing device, content of the linked webpage using the URL;

generating, by the computing device, answers to the questions using the retrieved content;

returning, by the computing device, the questions and the answers to the browser such that the browser displays the questions and the answers in the webpage;

receiving feedback from a user about the questions and the answers;

in response to the feedback indicating the user likes a particular one of the questions, determining a question type of the particular one of the questions and adjusting automated question generation algorithms in a manner that makes the automated question generation algorithms more likely to generate the determined question type for the user; and

in response to the feedback indicating the user dislikes a particular one of the questions, determining a question type of the particular one of the questions and adjusting automated question generation algorithms in a manner that makes the automated question generation algorithms less likely to generate the determined question type for the user.

2. The method of claim 1 , wherein the text is extracted from hypertext in the webpage and the URL is defined in a hyperlink associated with the hypertext.

3. The method of claim 1 , wherein the generating the questions comprises:

determining objects in the text using linguistic analysis; and

generating the questions using the objects and automated question generation (QG).

4. The method of claim 3 , wherein the linguistic analysis comprises sentence analysis and grammar analysis of the text.

5. The method of claim 3 , wherein:

the determining objects comprises determining common nouns; and

the questions are questions about the determined common nouns.

6. The method of claim 1 , wherein the generating the answers comprises:

generating the answers using the retrieved content and automated question answering (QA).

7. The method of claim 1 , wherein:

the text and the URL are received in response to a user hovering a mouse cursor over hypertext in the webpage; and

the browser is configured to display the questions and the answers in a cursor pop-up window while the mouse cursor is still over the hypertext.

8. The method of claim 1 , wherein the text is from one of plural hypertext headlines included in the webpage, and further comprising preprocessing the plural hypertext headlines in response to a user first visiting the webpage, the preprocessing comprising:

generating respective lists of question-answer pairs for each of plural hypertext headlines; and

storing the respective lists of question-answer pairs in a cache.

9. The method of claim 1 , further comprising:

determining the text is in the form of a particular question; and

wherein the generating the answers comprises generating an answer to the particular question using the retrieved content; and

including the particular question and the answer to the particular question in the questions and the answers that are returned to the browser for display in the browser.

10. A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

receive text extracted from a webpage in a browser and a Uniform Resource Locator (URL) of a linked webpage associated with the text;

generate a question based on the text;

retrieve content of the linked webpage using the URL;

generate answers to the question using the retrieved content;

determine a highest ranked answer based on respective confidence scores of each of the answers; and

return the question and the highest ranked answer to the browser such that the browser displays the question and the highest ranked answer in the webpage,

wherein the text is from one of plural hypertext headlines included in the webpage, and further comprising preprocessing the plural hypertext headlines in response to a user first visiting the webpage, the preprocessing comprising:

generating respective lists of question-answer pairs for each of plural hypertext headlines; and

storing the respective lists of question-answer pairs in a cache.

11. The computer program product of claim 10 , wherein the text is extracted from hypertext in the webpage and the URL is defined in a hyperlink associated with the hypertext.

12. The computer program product of claim 10 , wherein the generating the question comprises:

determining an object in the text using linguistic analysis; and

generating the question using the object and automated question generation (QG).

13. The computer program product of claim 10 , wherein the generating the answers comprises:

generating the answers using the retrieved content and automated question answering (QA).

14. The computer program product of claim 10 , wherein:

the text and the URL are received in response to a user hovering a mouse cursor over hypertext in the webpage; and

the browser is configured to display the question and the highest ranked answer in a cursor pop-up window while the mouse cursor is still over the hypertext.

15. A system comprising:

a processor, a computer readable memory, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

receive text extracted from a webpage in a browser and a Uniform Resource Locator (URL) of a linked webpage associated with the text;

generate a question based on the text;

retrieve content of the linked webpage using the URL;

generate answers to the question using the retrieved content;

determine a highest ranked answer based on respective confidence scores of each of the answers; and

return the question and the highest ranked answer to the browser such that the browser displays the question and the highest ranked answer in the webpage,

wherein the text is from one of plural hypertext headlines included in the webpage, and further comprising preprocessing the plural hypertext headlines in response to a user first visiting the webpage, the preprocessing comprising:

generating respective lists of question-answer pairs for each of plural hypertext headlines; and

storing the respective lists of question-answer pairs in a cache.

16. The system of claim 15 , wherein the returning is performed in response to determining that a confidence score of the highest ranked answer exceeds a predefined threshold value.

17. The system of claim 15 , wherein the generating the question comprises:

determining an object in the text using linguistic analysis; and

generating the question using the object and automated question generation (QG).

18. The system of claim 15 , wherein the generating the answers comprises:

generating the answers using the retrieved content and automated question answering (QA).

19. The system of claim 15 , wherein:

the text and the URL are received in response to a user hovering a mouse cursor over hypertext in the webpage; and

the browser is configured to display the question and the highest ranked answer in a cursor pop-up window while the mouse cursor is still over the hypertext.