Informatics Report Series
|
|
|
|
|
|
Title:Bootstrapping Statistical Parsers from Small Datasets |
Authors:
Mark Steedman
; Miles Osborne
; Anoop Sarkar
; Stephen Clark
; Rebecca Hwa
; Julia Hockenmaier
; Paul Ruhlen
|
Date: 2003 |
Publication Title:EACL |
Publisher:Association for Computational Linguistics |
Publication Type:Conference Paper
Publication Status:Published
|
Page Nos:331-338
|
DOI:10.3115/1067807.1067851
ISBN/ISSN:1-333-56789-8
|
- Abstract:
-
We present a practical co-training method for bootstrapping statistical parsers using a small amount of manually parsed training material and a much larger pool of raw sentences. Experimental results show that unlabelled sentences can be used to improve the performance of statistical parsers. In addition, we consider the problem of bootstrapping parsers when the manually parsed training material is in a different domain to either the raw sentences or the testing material. We show that bootstrapping continues to be useful, even though no manually produced parses fom the target domain are used.
- Links To Paper
- 1st Link
- Bibtex format
- @InProceedings{EDI-INF-RR-1019,
- author = {
Mark Steedman
and Miles Osborne
and Anoop Sarkar
and Stephen Clark
and Rebecca Hwa
and Julia Hockenmaier
and Paul Ruhlen
},
- title = {Bootstrapping Statistical Parsers from Small Datasets},
- book title = {EACL},
- publisher = {Association for Computational Linguistics},
- year = 2003,
- pages = {331-338},
- doi = {10.3115/1067807.1067851},
- url = {http://acl.ldc.upenn.edu/E/E03/E03-1008.pdf},
- }
|