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.
|Title of host publication||Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics|
|Publisher||Association for Computational Linguistics|
|Publication status||Published - 2018|
|Event||The 56th Annual Meeting of the Association for Computational Linguistics - Melbourne, Melbourne, Australia|
Duration: 15 Jul 2018 → 20 Jul 2018
|Conference||The 56th Annual Meeting of the Association for Computational Linguistics|
|Period||15/07/2018 → 20/07/2018|