Reinforced Mnemonic Reader for Machine Comprehension

05/08/2017
by   Minghao Hu, et al.
0

In this paper, we introduce the Reinforced Mnemonic Reader for machine comprehension (MC) task, which aims to answer a query about a given context document. We propose several novel mechanisms that address critical problems in MC that are not adequately solved by previous works, such as enhancing the capacity of encoder, modeling long-term dependencies of contexts, refining the predicted answer span, and directly optimizing the evaluation metric. Extensive experiments on TriviaQA and Stanford Question Answering Dataset (SQuAD) show that our model achieves state-of-the-art results.

READ FULL TEXT
research
11/05/2016

Bidirectional Attention Flow for Machine Comprehension

Machine comprehension (MC), answering a query about a given context para...
research
06/29/2017

Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

We develop a technique for transfer learning in machine comprehension (M...
research
10/08/2017

Smarnet: Teaching Machines to Read and Comprehend Like Human

Machine Comprehension (MC) is a challenging task in Natural Language Pro...
research
03/24/2018

Multi-range Reasoning for Machine Comprehension

We propose MRU (Multi-Range Reasoning Units), a new fast compositional e...
research
07/28/2017

MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension

Machine comprehension(MC) style question answering is a representative p...
research
12/13/2016

Multi-Perspective Context Matching for Machine Comprehension

Previous machine comprehension (MC) datasets are either too small to tra...
research
10/31/2017

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

Traditional models for question answering optimize using cross entropy l...

Please sign up or login with your details

Forgot password? Click here to reset