A Neural Probabilistic Structured-Prediction Method for Transition-Based Natural Language Processing

Hao Zhou, Yue Zhang, Chuan Cheng, Shujian Huang, Xinyu Dai, Jiajun Chen

JAIR 2017 pp. 703-729

doi:10.1613/JAIR.5259 /jair/2017/zhou2017jair-neural/

Abstract

We propose a neural probabilistic structured-prediction method for transition-based natural language processing, which integrates beam search and contrastive learning. The method uses a global optimization model, which can leverage arbitrary features over non-local context. Beam search is used for efficient heuristic decoding, and contrastive learning is performed for adjusting the model according to search errors. When evaluated on both chunking and dependency parsing tasks, the proposed method achieves significant accuracy improvements over the locally normalized greedy baseline on the two tasks, respectively.

PDF JAIR Semantic Scholar

Cite

Text

Zhou et al. "A Neural Probabilistic Structured-Prediction Method for Transition-Based Natural Language Processing." Journal of Artificial Intelligence Research, 2017. doi:10.1613/JAIR.5259

Markdown

[Zhou et al. "A Neural Probabilistic Structured-Prediction Method for Transition-Based Natural Language Processing." Journal of Artificial Intelligence Research, 2017.](https://mlanthology.org/jair/2017/zhou2017jair-neural/) doi:10.1613/JAIR.5259

BibTeX

@article{zhou2017jair-neural,
  title     = {{A Neural Probabilistic Structured-Prediction Method for Transition-Based Natural Language Processing}},
  author    = {Zhou, Hao and Zhang, Yue and Cheng, Chuan and Huang, Shujian and Dai, Xinyu and Chen, Jiajun},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2017},
  pages     = {703-729},
  doi       = {10.1613/JAIR.5259},
  volume    = {58},
  url       = {https://mlanthology.org/jair/2017/zhou2017jair-neural/}
}