Unsupervised Deep Learning based Multiple Choices Question Answering: Start Learning from Basic Knowledge

10/21/2020
by   Chi-Liang Liu, et al.
23

In this paper, we study the possibility of almost unsupervised Multiple Choices Question Answering (MCQA). Starting from very basic knowledge, MCQA model knows that some choices have higher probabilities of being correct than the others. The information, though very noisy, guides the training of an MCQA model. The proposed method is shown to outperform the baseline approaches on RACE and even comparable with some supervised learning approaches on MC500.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2019

Advances in Natural Language Question Answering: A Review

Question Answering has recently received high attention from artificial ...
research
08/31/2021

Unsupervised Open-Domain Question Answering

Open-domain Question Answering (ODQA) has achieved significant results i...
research
10/29/2019

Sentence Embeddings for Russian NLU

We investigate the performance of sentence embeddings models on several ...
research
12/06/2018

Deep Learning Approaches for Question Answering on Knowledge Bases: an evaluation of architectural design choices

The task of answering natural language questions over knowledge bases ha...
research
12/06/2018

Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases

The task of answering natural language questions over knowledge bases ha...
research
10/03/2018

Transfer Learning via Unsupervised Task Discovery for Visual Question Answering

We study how to leverage off-the-shelf visual and linguistic data to cop...

Please sign up or login with your details

Forgot password? Click here to reset