Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Strong Baselines for Neural Semi-supervised Learning under Domain Shift

About

Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training. Extensive experiments on two benchmarks are negative: while our novel method establishes a new state-of-the-art for sentiment analysis, it does not fare consistently the best. More importantly, we arrive at the somewhat surprising conclusion that classic tri-training, with some additions, outperforms the state of the art. We conclude that classic approaches constitute an important and strong baseline.

Sebastian Ruder, Barbara Plank• 2018

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy54.4
78
Part-of-Speech TaggingWSJ (test)
Accuracy97.37
51
POS TaggingWSJ (dev)
Accuracy97.37
11
POS TaggingSANCL 1.0 (dev)
Accuracy (Answers)89.45
11
Sentiment AnalysisAmazon Sentiment Analysis (test)
D Score78.14
8
POS TaggingSANCL (test)
Accuracy (Answers)0.9053
7
Showing 6 of 6 rows

Other info

Code

Follow for update