DeepAI
Log In Sign Up

Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation

06/21/2021
by   Yang Deng, et al.
0

In this work, we propose a novel and easy-to-apply data augmentation strategy, namely Bilateral Generation (BiG), with a contrastive training objective for improving the performance of ranking question answer pairs with existing labeled data. In specific, we synthesize pseudo-positive QA pairs in contrast to the original negative QA pairs with two pre-trained generation models, one for question generation, the other for answer generation, which are fine-tuned on the limited positive QA pairs from the original dataset. With the augmented dataset, we design a contrastive training objective for learning to rank question answer pairs. Experimental results on three benchmark datasets, namely TREC-QA, WikiQA, and ANTIQUE, show that our method significantly improves the performance of ranking models by making full use of existing labeled data and can be easily applied to different ranking models.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/05/2021

End-to-End Video Question-Answer Generation with Generator-Pretester Network

We study a novel task, Video Question-Answer Generation (VQAG), for chal...
07/07/2022

Supervised Contrastive Learning Approach for Contextual Ranking

Contextual ranking models have delivered impressive performance improvem...
11/16/2022

Consecutive Question Generation via Dynamic Multitask Learning

In this paper, we propose the task of consecutive question generation (C...
10/14/2021

Retrieval-guided Counterfactual Generation for QA

Deep NLP models have been shown to learn spurious correlations, leaving ...
08/23/2022

Unsupervised Question Answering via Answer Diversifying

Unsupervised question answering is an attractive task due to its indepen...
06/08/2021

Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading

We propose a simple and effective strategy for data augmentation for low...
09/17/2020

Self-supervised pre-training and contrastive representation learning for multiple-choice video QA

Video Question Answering (Video QA) requires fine-grained understanding ...