Cross-Domain Generalization Through Memorization: A Study of Nearest Neighbors in Neural Duplicate Question Detection

11/22/2020
by   Yadollah Yaghoobzadeh, et al.
0

Duplicate question detection (DQD) is important to increase efficiency of community and automatic question answering systems. Unfortunately, gathering supervised data in a domain is time-consuming and expensive, and our ability to leverage annotations across domains is minimal. In this work, we leverage neural representations and study nearest neighbors for cross-domain generalization in DQD. We first encode question pairs of the source and target domain in a rich representation space and then using a k-nearest neighbour retrieval-based method, we aggregate the neighbors' labels and distances to rank pairs. We observe robust performance of this method in different cross-domain scenarios of StackExchange, Spring and Quora datasets, outperforming cross-entropy classification in multiple cases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/27/2013

Cross-Domain Sparse Coding

Sparse coding has shown its power as an effective data representation me...
research
09/08/2019

Cross Domain Image Matching in Presence of Outliers

Cross domain image matching between image collections from different sou...
research
02/06/2020

On the limits of cross-domain generalization in automated X-ray prediction

This large scale study focuses on quantifying what X-rays diagnostic pre...
research
09/19/2018

Privacy-Preserving DDoS Attack Detection Using Cross-Domain Traffic in Software Defined Networks

Existing distributed denial-of-service attack detection in software defi...
research
05/10/2018

Neural Best-Buddies: Sparse Cross-Domain Correspondence

Correspondence between images is a fundamental problem in computer visio...
research
07/28/2020

Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors

Domain generalization (DG) deals with the problem of domain shift where ...

Please sign up or login with your details

Forgot password? Click here to reset