|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2020 Vol.21 No.9 P.1346-1355
Hybrid embedding and joint training of stacked encoder for opinion question machine reading comprehension
Abstract: Opinion question machine reading comprehension (MRC) requires a machine to answer questions by analyzing corresponding passages. Compared with traditional MRC tasks where the answer to every question is a segment of text in corresponding passages, opinion question MRC is more challenging because the answer to an opinion question may not appear in corresponding passages but needs to be deduced from multiple sentences. In this study, a novel framework based on neural networks is proposed to address such problems, in which a new hybrid embedding training method combining text features is used. Furthermore, extra attention and output layers which generate auxiliary losses are introduced to jointly train the stacked recurrent neural networks. To deal with imbalance of the dataset, irrelevancy of question and passage is used for data augmentation. Experimental results show that the proposed method achieves state-of-the-art performance. We are the biweekly champion in the opinion question MRC task in Artificial Intelligence Challenger 2018 (AIC2018).
Key words: Machine reading comprehension, Neural networks, Joint training, Data augmentation
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.1900571
CLC number:
TP391.1
Download Full Text:
Downloaded:
6226
Clicked:
4593
Cited:
0
On-line Access:
2020-09-09
Received:
2019-10-19
Revision Accepted:
2020-03-16
Crosschecked:
2020-08-10