基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling)
Yujiao Han (韩玉蛟), Zhiyong Luo (罗智勇), Mingming Zhang (张明明), Zhilin Zhao (赵志琳), Qing Zhang (张青)
Abstract
“机器阅读理解(Machine Reading Comprehension, MRC)任务旨在让机器回答给定上下文的问题来测试机器理解自然语言的能力。目前,基于大规模预训练语言模型的神经机器阅读理解模型已经取得重要进展,但在涉及答案要素、线索要素和问题要素跨标点句、远距离关联时,答案抽取的准确率还有待提升。本文通过篇章内话头话体结构分析,建立标点句间远距离关联关系、补全共享缺失成分,辅助机器阅读理解答案抽取;设计和实现融合话头话体结构信息的机器阅读理解模型,在公开数据集CMRC2018上的实验结果表明,模型的F1值相对于基线模型提升2.4%,EM值提升6%。”- Anthology ID:
- 2022.ccl-1.57
- Volume:
- Proceedings of the 21st Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Nanchang, China
- Editors:
- Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 634–643
- Language:
- Chinese
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.ccl-1.57/
- DOI:
- Cite (ACL):
- Yujiao Han, Zhiyong Luo, Mingming Zhang, Zhilin Zhao, and Qing Zhang. 2022. 基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 634–643, Nanchang, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling) (Han et al., CCL 2022)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.ccl-1.57.pdf
- Data
- CLUE, DuReader