ML Anthology

Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction

Benjamin Rozenfeld, Ronen Feldman
IJCAI 2011 pp. 1890-1895
doi:10.5591/978-1-57735-516-8/IJCAI11-316 /ijcai/2011/rozenfeld2011ijcai-unsupervised/

Abstract

The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domain- and relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

PDF IJCAI Semantic Scholar

Cite

Text

Rozenfeld and Feldman. "Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-316

Markdown

[Rozenfeld and Feldman. "Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/rozenfeld2011ijcai-unsupervised/) doi:10.5591/978-1-57735-516-8/IJCAI11-316

BibTeX

@inproceedings{rozenfeld2011ijcai-unsupervised,
  title     = {{Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction}},
  author    = {Rozenfeld, Benjamin and Feldman, Ronen},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2011},
  pages     = {1890-1895},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-316},
  url       = {https://mlanthology.org/ijcai/2011/rozenfeld2011ijcai-unsupervised/}
}