3 search results - page 1 / 1 » Subdomain Sensitive Statistical Parsing using Raw Corpora |
LREC
2008
13 years 6 months ago
2008
Modern statistical parsers are trained on large annotated corpora (treebanks). These treebanks usually consist of sentences addressing different subdomains (e.g. sports, politics,...
EMNLP
2007
13 years 6 months ago
2007
One may need to build a statistical parser for a new language, using only a very small labeled treebank together with raw text. We argue that bootstrapping a parser is most promis...
FLAIRS
2003
13 years 6 months ago
2003
One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model exclud...