ASV-Label
Login

16px-feed-icon Veröffentlichungen View this page in English

Hae2010b

Abstract:

This paper presents an algorithm for unsupervised co-occurrence based parsing that improves and extends existing approaches. The proposed algorithm induces a contextfree grammar of the language in question in an iterative manner. The resulting structure of a sentence will be given as a hierarchical arrangement of constituents. Although this algorithm does not use any a priori knowledge about the language, it is able to detect heads, modifiers and a phrase type’s different compound composition possibilities. For evaluation purposes, the algorithm is applied to manually annotated part-of-speech tags (POS tags) as well as to word classes induced by an unsupervised part-of-speech tagger.

Type: Inproceedings

Author: Hänig, C.
Title: Improvements in Unsupervised Co-Occurrence Based Parsing
Booktitle: Proceedings of the Fourteenth Conference on Computational Natural Language Learning (CoNLL 2010)
Year: 2010
Pages:1--8
Publisher:Association for Computational Linguistics
Address:
@INPROCEEDINGS{Hae2010b,
AUTHOR = {Hänig, C.},
TITLE = {Improvements in Unsupervised Co-Occurrence Based Parsing},
BOOKTITLE = {Proceedings of the Fourteenth Conference on Computational Natural Language Learning (CoNLL 2010)},
YEAR = {2010},
PAGES = {1--8},
PUBLISHER = {Association for Computational Linguistics}
}