Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval

04/18/2021
by   Devang Kulshreshtha, et al.
0

In this paper, we propose a new domain adaptation method called back-training, a superior alternative to self-training. While self-training results in synthetic training data of the form quality inputs aligned with noisy outputs, back-training results in noisy inputs aligned with quality outputs. Our experimental results on unsupervised domain adaptation of question generation and passage retrieval models from Natural Questions domain to the machine learning domain show that back-training outperforms self-training by a large margin: 9.3 BLEU-1 points on generation, and 7.9 accuracy points on top-1 retrieval. We release MLQuestions, a domain-adaptation dataset for the machine learning domain containing 50K unaligned passages and 35K unaligned questions, and 3K aligned passage and question pairs. Our data and code are available at https://github.com/McGill-NLP/MLQuestions

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/26/2022

1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsuperv...
research
06/23/2017

Model Selection with Nonlinear Embedding for Unsupervised Domain Adaptation

Domain adaptation deals with adapting classifiers trained on data from a...
research
08/27/2020

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

The divergence between labeled training data and unlabeled testing data ...
research
08/25/2023

Unsupervised Domain Adaptation for Anatomical Landmark Detection

Recently, anatomical landmark detection has achieved great progresses on...
research
06/14/2022

Slimmable Domain Adaptation

Vanilla unsupervised domain adaptation methods tend to optimize the mode...
research
10/15/2020

Self-Supervised Domain Adaptation with Consistency Training

We consider the problem of unsupervised domain adaptation for image clas...
research
12/28/2020

Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy

Reducing feature redundancy has shown beneficial effects for improving t...

Please sign up or login with your details

Forgot password? Click here to reset