Abstract
In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model for semi-supervised learning of sequential structured prediction problems. Our NCRF-AE consists of two parts: an encoder which is a CRF model enhanced by deep neural networks, and a decoder which is a generative model trying to reconstruct the input. Our model has a unified structure with different loss functions for labeled and unlabeled data with shared parameters. We developed a variation of the EM algorithm for optimizing both the encoder and the decoder simultaneously by decoupling their parameters. Our Experimental results over the Part-of-Speech (POS) tagging task on eight different languages, show that our model can outperform competitive systems in both supervised and semi-supervised scenarios.- Anthology ID:
- D17-1179
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1701–1711
- Language:
- URL:
- https://aclanthology.org/D17-1179
- DOI:
- 10.18653/v1/D17-1179
- Cite (ACL):
- Xiao Zhang, Yong Jiang, Hao Peng, Kewei Tu, and Dan Goldwasser. 2017. Semi-supervised Structured Prediction with Neural CRF Autoencoder. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1701–1711, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Semi-supervised Structured Prediction with Neural CRF Autoencoder (Zhang et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D17-1179.pdf
- Code
- cosmozhang/NCRF-AE