Papers with manual summarization of
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for summarizing long questions are difficult due to the lack of training data and the complexity of the related subtasks. |
| Approach: | They propose a reinforcement learning-based framework for abstractive question summarization that rewards question-type identification and question-focus recognition for regularizing the question generation model. |
| Outcome: | The proposed method achieves higher performance over state-of-the-art models on two benchmark datasets. |