Question Generation by Transformers
This addresses the problem of automating question creation for educational or QA systems, but it is incremental as it applies an existing transformer method to a new dataset.
The authors tackled automatic question generation from Wikipedia passages using transformers, achieving an average of 8 words per question with mostly grammatically correct outputs, though they noted a high word error rate compared to original SQuAD questions.
A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). The model was trained on the inverted Stanford Question Answering Dataset (SQuAD), which is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles. After training, the question generation model is able to generate simple questions relevant to unseen passages and answers containing an average of 8 words per question. The word error rate (WER) was used as a metric to compare the similarity between SQuAD questions and the model-generated questions. Although the high average WER suggests that the questions generated differ from the original SQuAD questions, the questions generated are mostly grammatically correct and plausible in their own right.