ML Anthology

Natural Language Grammar Induction Using a Constituent-Context Model

Dan Klein, Christopher D. Manning
NeurIPS 2001 pp. 35-42
/neurips/2001/klein2001neurips-natural/

Abstract

This paper presents a novel approach to the unsupervised learning of syn- tactic analyses of natural language text. Most previous work has focused on maximizing likelihood according to generative PCFG models. In con- trast, we employ a simpler probabilistic model over trees based directly on constituent identity and linear context, and use an EM-like iterative procedure to induce structure. This method produces much higher qual- ity analyses, giving the best published results on the ATIS dataset. 1 Overview

PDF NeurIPS Semantic Scholar

Cite

Text

Klein and Manning. "Natural Language Grammar Induction Using a Constituent-Context Model." Neural Information Processing Systems, 2001.

Markdown

[Klein and Manning. "Natural Language Grammar Induction Using a Constituent-Context Model." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/klein2001neurips-natural/)

BibTeX

@inproceedings{klein2001neurips-natural,
  title     = {{Natural Language Grammar Induction Using a Constituent-Context Model}},
  author    = {Klein, Dan and Manning, Christopher D.},
  booktitle = {Neural Information Processing Systems},
  year      = {2001},
  pages     = {35-42},
  url       = {https://mlanthology.org/neurips/2001/klein2001neurips-natural/}
}