MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering
[article]
Tolgahan Cakaloglu, Xiaowei Xu
2019
arXiv
pre-print
The empirical study shows that MRNN with the duplex attention is significantly superior to existing models used for ad-hoc retrieval on benchmark datasets including SQuAD, WikiQA, QUASAR, and TrecQA. ...
It requires a good understanding of the query and all the documents in a corpus, which is difficult because the meaning of natural language texts depends on the context, syntax,and semantics. ...
DrQA [13] is built on top of two component; a Document Retriever and a Document Reader respectively. The Document Retriever is a TF-IDF [2] retrieval system built upon Wikipedia corpus. ...
arXiv:1911.00964v1
fatcat:vxhhe4fbwrhcxbgdit36mwomqy