Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2203.14187 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929525834645504 |
|---|---|
| author | Zhao, Zhenjie Hou, Yufang Wang, Dakuo Yu, Mo Liu, Chengzhong Ma, Xiaojuan |
| author_facet | Zhao, Zhenjie Hou, Yufang Wang, Dakuo Yu, Mo Liu, Chengzhong Ma, Xiaojuan |
| contents | Generating educational questions of fairytales or storybooks is vital for improving children's literacy ability. However, it is challenging to generate questions that capture the interesting aspects of a fairytale story with educational meaningfulness. In this paper, we propose a novel question generation method that first learns the question type distribution of an input story paragraph, and then summarizes salient events which can be used to generate high-cognitive-demand questions. To train the event-centric summarizer, we finetune a pre-trained transformer-based sequence-to-sequence model using silver samples composed by educational question-answer pairs. On a newly proposed educational question answering dataset FairytaleQA, we show good performance of our method on both automatic and human evaluation metrics. Our work indicates the necessity of decomposing question type distribution learning and event-centric summary generation for educational question generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_14187 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization Zhao, Zhenjie Hou, Yufang Wang, Dakuo Yu, Mo Liu, Chengzhong Ma, Xiaojuan Computation and Language Human-Computer Interaction Generating educational questions of fairytales or storybooks is vital for improving children's literacy ability. However, it is challenging to generate questions that capture the interesting aspects of a fairytale story with educational meaningfulness. In this paper, we propose a novel question generation method that first learns the question type distribution of an input story paragraph, and then summarizes salient events which can be used to generate high-cognitive-demand questions. To train the event-centric summarizer, we finetune a pre-trained transformer-based sequence-to-sequence model using silver samples composed by educational question-answer pairs. On a newly proposed educational question answering dataset FairytaleQA, we show good performance of our method on both automatic and human evaluation metrics. Our work indicates the necessity of decomposing question type distribution learning and event-centric summary generation for educational question generation. |
| title | Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2203.14187 |