@inproceedings{861844c9a04e47ef81bf46c2942eef6f,
title = "Coarse-To-Fine Document Ranking for Multi-Document Reading Comprehension with Answer-Completion",
abstract = "Multi-document machine reading comprehension (MRC) has two characteristics compared with traditional MRC: 1) many documents are irrelevant to the question; 2) the length of the answer is relatively longer. However, in existing models, not only key ranking metrics at different granularity are ignored, but also few current methods can predict the complete answer as they mainly deal with the start and end token of each answer equally. To address these issues, we propose a model that can fuse coarse-To-fine ranking processes based on document chunks to distinguish various documents more effectively. Furthermore, we incorporate an answer-completion strategy to predict complete answers by modifying loss function. The experimental results show that our model for multi-document MRC makes a significant improvement with 7.4% and 13% respectively on Rouge-L and BLEU-4 score, in contrast with the current models on a public Chinese dataset, DuReader.",
keywords = "answer prediction, document ranking, multi-document reading comprehension",
author = "Hongyu Liu and Shumin Shi and Heyan Huang",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 23rd International Conference on Asian Language Processing, IALP 2019 ; Conference date: 15-11-2019 Through 17-11-2019",
year = "2019",
month = nov,
doi = "10.1109/IALP48816.2019.9037670",
language = "English",
series = "Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "407--412",
editor = "Man Lan and Yuanbin Wu and Minghui Dong and Yanfeng Lu and Yan Yang",
booktitle = "Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019",
address = "United States",
}