Learning and Parsing Stochastic Unification-Based Grammars

Abstract

Stochastic Unification-Based Grammars combine knowledge-rich and data-rich approaches to natural language processing. This provides a rich structure to the learning and parsing (decoding) tasks that can be described with undirected graphical models. While most work to date has treated parsing as a straight-forward multi-class classification problem, we are beginning to see how this structure can be exploited in learning and parsing. Exploiting this structure is likely to become more important as the research focus moves from parsing to more realistic tasks such as machine translation and summarization.

Cite

Text

Johnson. "Learning and Parsing Stochastic Unification-Based Grammars." Annual Conference on Computational Learning Theory, 2003. doi:10.1007/978-3-540-45167-9_49

Markdown

[Johnson. "Learning and Parsing Stochastic Unification-Based Grammars." Annual Conference on Computational Learning Theory, 2003.](https://mlanthology.org/colt/2003/johnson2003colt-learning/) doi:10.1007/978-3-540-45167-9_49

BibTeX

@inproceedings{johnson2003colt-learning,
  title     = {{Learning and Parsing Stochastic Unification-Based Grammars}},
  author    = {Johnson, Mark},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2003},
  pages     = {671-683},
  doi       = {10.1007/978-3-540-45167-9_49},
  url       = {https://mlanthology.org/colt/2003/johnson2003colt-learning/}
}