![]() ![]() Association for Computational Linguistics. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6896–6906, Dublin, Ireland. CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation. Anthology ID: 2022.acl-long.475 Volume: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Month: May Year: 2022 Address: Dublin, Ireland Venue: ACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 6896–6906 Language: URL: DOI: 10.18653/v1/2022.acl-long.475 Bibkey: fei-etal-2022-cqg Cite (ACL): Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, and Xuanjing Huang. Experiment results show that our model greatly improves performance, which also outperforms the state-of-the-art model about 25% by 5 BLEU points on HotpotQA. In addition, we introduce a novel controlled Transformer-based decoder to guarantee that key entities appear in the questions. CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions. To address this challenge, we propose the CQG, which is a simple and effective controlled framework. ![]() However, most models can not ensure the complexity of generated questions, so they may generate shallow questions that can be answered without multi-hop reasoning. Current models with state-of-the-art performance have been able to generate the correct questions corresponding to the answers. ![]() Abstract Multi-hop question generation focuses on generating complex questions that require reasoning over multiple pieces of information of the input passage. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |