Dynamic evaluation of event participants using a smart context-based quiz system
Methods, apparatus, and processor-readable storage media for generating context-based question-answer pairs by applying artificial intelligence techniques to context-related data are provided herein. An example computer-implemented method includes obtaining multi-modal data pertaining to a given event, and removing noise from the multi-modal data by applying filtering techniques to the multi-modal data, thereby generating filtered multi-modal data; creating a comprehensive set of multi-modal data pertaining to at least a portion of the given event by aggregating the filtered multi-modal data in accordance with topic modelling techniques and removing any items of duplicate filtered multi-modal data; dynamically generating question-answer pairs related to the given event by applying machine reading comprehension-based artificial intelligence models to the comprehensive set of multi-modal data; and outputting at least a portion of the questions from the question-answer pairs to one or more participants of the given event.
1. A computer-implemented method comprising:
obtaining multi-modal data from one or more data sources, wherein the multi-modal data pertains to a given event and comprise audio data, video data, and image data;
creating a comprehensive set of multi-modal data pertaining to at least a portion of the given event by processing at least a portion of the multi-modal data in accordance with one or more topic modelling techniques, wherein processing comprises: processing at least a portion of the audio data using one or more machine learning compression algorithms, and processing at least a portion of the video data and at least a portion of the image data using one or more convolutional neural network-based image classification algorithms;
dynamically generating one or more question-answer pairs related to the given event by applying one or more machine reading comprehension-based artificial intelligence models to the comprehensive set of multi-modal data;
outputting at least a portion of the one or more questions from the one or more question-answer pairs to one or more participants of the given event; and
automatically training, based at least in part on one or more sets of labeled multi-modal data in connection with the one or more question-answer pairs, at least a portion of the one or more machine learning compression algorithms and at least a portion of the one or more convolutional neural network-based image classification algorithms;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The computer-implemented method of claim 1 , wherein the multi-modal data further comprises text data.
3. The computer-implemented method of claim 1 , wherein dynamically generating the one or more question-answer pairs comprises dynamically generating question-answer pairs of varying difficulty.
4. The computer-implemented method of claim 1 , wherein dynamically generating the one or more question-answer pairs comprises utilizing context information pertaining to the one or more participants of the given event.
5. The computer-implemented method of claim 4 , wherein the context information comprises a type of device being used by the one or more participants.
6. The computer-implemented method of claim 1 , further comprising:
attributing a confidence value to each answer provided by the one or more participants in response to the one or more questions.
7. The computer-implemented method of claim 6 , further comprising:
determining one or more features attributed to the one or more participants of the given event based at least in part on the confidence values.
8. The computer-implemented method of claim 7 , wherein the one or more features comprise attentiveness of the one or more participants.
9. The computer-implemented method of claim 7 , wherein the one or more features comprise comprehension by the one or more participants.
10. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to obtain multi-modal data from one or more data sources, wherein the multi-modal data pertains to a given event and comprise audio data, video data, and image data;
to create a comprehensive set of multi-modal data pertaining to at least a portion of the given event by processing at least a portion of the multi-modal data in accordance with one or more topic modelling techniques, wherein processing comprises: processing at least a portion of the audio data using one or more machine learning compression algorithms, and processing at least a portion of the video data and at least a portion of the image data using one or more convolutional neural network-based image classification algorithms;
to dynamically generate one or more question-answer pairs related to the given event by applying one or more machine reading comprehension-based artificial intelligence models to the comprehensive set of multi-modal data;
to output at least a portion of the one or more questions from the one or more question-answer pairs to one or more participants of the given event; and
to automatically train, based at least in part on one or more sets of labeled multi-modal data in connection with the one or more question-answer pairs, at least a portion of the one or more machine learning compression algorithms and at least a portion of the one or more convolutional neural network-based image classification algorithms.
11. The non-transitory processor-readable storage medium of claim 10 , wherein dynamically generating the one or more question-answer pairs comprises dynamically generating question-answer pairs of varying difficulty.
12. The non-transitory processor-readable storage medium of claim 10 , wherein dynamically generating the one or more question-answer pairs comprises utilizing context information pertaining to the one or more participants of the given event.
13. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain multi-modal data from one or more data sources, wherein the multi-modal data pertains to a given event and comprise audio data, video data, and image data;
to create a comprehensive set of multi-modal data pertaining to at least a portion of the given event by processing at least a portion of the multi-modal data in accordance with one or more topic modelling techniques, wherein processing comprises: processing at least a portion of the audio data using one or more machine learning compression algorithms, and processing at least a portion of the video data and at least a portion of the image data using one or more convolutional neural network-based image classification algorithms;
to dynamically generate one or more question-answer pairs related to the given event by applying one or more machine reading comprehension-based artificial intelligence models to the comprehensive set of multi-modal data;
to output at least a portion of the one or more questions from the one or more question-answer pairs to one or more participants of the given event; and
to automatically train, based at least in part on one or more sets of labeled multi-modal data in connection with the one or more question-answer pairs, at least a portion of the one or more machine learning compression algorithms and at least a portion of the one or more convolutional neural network-based image classification algorithms.
14. The apparatus of claim 13 , wherein dynamically generating the one or more question-answer pairs comprises dynamically generating question-answer pairs of varying difficulty.
15. The apparatus of claim 13 , wherein dynamically generating the one or more question-answer pairs comprises utilizing context information pertaining to the one or more participants of the given event.
16. The apparatus of claim 13 , the at least one processing device being further configured:
to attribute a confidence value to each answer provided by the one or more participants in response to the one or more questions; and
to determine one or more features attributed to the one or more participants of the given event based at least in part on the confidence values.
17. The apparatus of claim 16 , wherein the one or more features comprise attentiveness of the one or more participants.
18. The apparatus of claim 16 , wherein the one or more features comprise comprehension by the one or more participants.
19. The apparatus of claim 13 , wherein the multi-modal data further comprises text data.
20. The non-transitory processor-readable storage medium of claim 10 , wherein the multi-modal data further comprises text data.