Asking questions the human way

Asking questions the human way

Problem being addressed

The ability to ask questions is important in both human and machine intelligence​,​ but the existing question generation models are ineffective at generating a large amount of high-quality question-answer pairs from unstructured text.

Solution

Question Generation, which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions. The system samples from the text multiple types of assistive information to guide question generation, generates diverse and controllable questions and removes low-quality generated data based on text entailment.

Advantages of this solution

The system dramatically outperforms state-of-the-art neural question generation models in terms of the generation quality, while being scalable in the meantime. With models trained on a relatively smaller amount of data, the system generate 2.8 million quality-assured question-answer pairs from a million sentences found in Wikipedia.

Possible New Application of the Work

/static/media/internet.b08c3623.png

Internet Industry

Question-answer generators improve the quality of the online search engine results, providing more accurate and relevant information for any search request.

/static/media/telecommunication.55054f1c.png

Telecommunications Industry

Novel algorithms that allow better training for question-answer that mimic human interaction are widely used to train chat bots, and can also improve the results for the voice assistants like Alexa.

Author of original research described in this blitzcard: Bang Liu, Haojie Wei, Di Niu, Haolan Chen, Yancheng He

question-mark-icon

Name of the author who conducted the original research that this blitzcard is based on.

Source URL: #############check-icon


search-iconBrowse all blitzcards