Unsupervised Parse Selection for HPSG

Rebecca Dridan, Timothy Baldwin
2010 Conference on Empirical Methods in Natural Language Processing  
Parser disambiguation with precision grammars generally takes place via statistical ranking of the parse yield of the grammar using a supervised parse selection model. In the standard process, the parse selection model is trained over a hand-disambiguated treebank, meaning that without a significant investment of effort to produce the treebank, parse selection is not possible. Furthermore, as treebanking is generally streamlined with parse selection models, creating the initial treebank without
more » ... a model requires more resources than subsequent treebanks. In this work, we show that, by taking advantage of the constrained nature of these HPSG grammars, we can learn a discriminative parse selection model from raw text in a purely unsupervised fashion. This allows us to bootstrap the treebanking process and provide better parsers faster, and with less resources.
dblp:conf/emnlp/DridanB10 fatcat:z6ynkhwianawxlgwstzvghhiei