SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.04362 · AAAI · 2020

Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

Han Guo, Mohit Bansal, Ramakanth Pasunuru

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results. Next, we develop a DistanceNet model which uses these distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task's loss function, so as to achieve better unsupervised domain adaptation. Finally, we extend this model to a novel DistanceNet-Bandit model, which employs a multiarmed bandit controller to dynamically switch between multiple source domains and allow the model to learn an optimal trajectory and mixture of domains for transfer to the lowresource target domain. We conduct experiments on popular sentiment analysis datasets with several diverse domains and show that our DistanceNet model, as well as its dynamic bandit variant, can outperform competitive baselines in the context of unsupervised domain adaptation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2001.04362")
get_code_for_paper("2001.04362")
have("2001.04362")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2001.04362.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2001.04362.svg)](https://syntology.ai/paper/2001.04362)

Connect an agent — have() is free.