Abstract
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 for part-of-speech tagging and sentiment analysis 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 for NLP. Hence classic approaches constitute an important and strong baseline.- Anthology ID:
- P18-1096
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1044–1054
- Language:
- URL:
- https://aclanthology.org/P18-1096
- DOI:
- 10.18653/v1/P18-1096
- Cite (ACL):
- Sebastian Ruder and Barbara Plank. 2018. Strong Baselines for Neural Semi-Supervised Learning under Domain Shift. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1044–1054, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (Ruder & Plank, ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P18-1096.pdf
- Code
- bplank/semi-supervised-baselines + additional community code
- Data
- Multi-Domain Sentiment Dataset v2.0