What is it about?
We proposed a stacked bidirectional Long Short-Term Memory (BiLSTM) neural network based on coattention mechanism to extract the interaction between questions and answers.
Featured Image
Why is it important?
The proposed methods effectively modeled the semantic understanding to generate a textual representation and also considered the semantic interaction between questions and answers
Perspectives
Experimental results confirm that the proposed model is efficient, particularly it achieves a higher average MAR (0.7613) and MRR (0.8401) on the TREC dataset.
Prof. Linqin CAI
Read the Original
This page is a summary of: A Stacked BiLSTM Neural Network Based on Coattention Mechanism for Question Answering, Computational Intelligence and Neuroscience, August 2019, Hindawi Publishing Corporation,
DOI: 10.1155/2019/9543490.
You can read the full text:
Resources
Contributors
The following have contributed to this page
