1 code implementation • Findings (NAACL) 2022 • Jin Qian, Bowei Zou, Mengxing Dong, Xiao Li, AiTi Aw, Yu Hong
Conversational Question Answering (ConvQA) is required to answer the current question, conditioned on the observable paragraph-level context and conversation history.
no code implementations • CCL 2020 • Jin Qian, Rongtao Huang, Bowei Zou, Yu Hong
生成式阅读理解是机器阅读理解领域一项新颖且极具挑战性的研究。与主流的抽取式阅读理解相比, 生成式阅读理解模型不再局限于从段落中抽取答案, 而是能结合问题和段落生成自然和完整的表述作为答案。然而, 现有的生成式阅读理解模型缺乏对答案在段落中的边界信息以及对问题类型信息的理解。为解决上述问题, 本文提出一种基于多任务学习的生成式阅读理解模型。该模型在训练阶段将答案生成任务作为主任务, 答案抽取和问题分类任务作为辅助任务进行多任务学习, 同时学习和优化模型编码层参数;在测试阶段加载模型编码层进行解码生成答案。实验结果表明, 答案抽取模型和问题分类模型能够有效提升生成式阅读理解模型的性能。
no code implementations • 22 Apr 2024 • Huan Bao, Kaimin Wei, Yongdong Wu, Jin Qian, Robert H. Deng
Then, it randomly chooses latent codes from the latent probability distribution for recovering the private data.
1 code implementation • 17 Nov 2022 • Pengpeng Zeng, Haonan Zhang, Lianli Gao, Xiangpeng Li, Jin Qian, Heng Tao Shen
Generating consecutive descriptions for videos, i. e., Video Captioning, requires taking full advantage of visual representation along with the generation process.