13 search results - page 1 / 3 » Recovering Latent Information in Treebanks |
COLING
2002
13 years 4 months ago
2002
Many recent statistical parsers rely on a preprocessing step which uses hand-written, corpus-specific rules to augment the training data with extra information. For example, head-...
COLING
2010
12 years 11 months ago
2010
Empty categories represent an important source of information in syntactic parses annotated in the generative linguistic tradition, but empty category recovery has only started to...
EMNLP
2006
13 years 6 months ago
2006
We study unsupervised methods for learning refinements of the nonterminals in a treebank. Following Matsuzaki et al. (2005) and Prescher (2005), we may for example split NP withou...
ACL
2004
13 years 6 months ago
2004
This paper describes an algorithm for detecting empty nodes in the Penn Treebank (Marcus et al., 1993), finding their antecedents, and assigning them function tags, without access...
ICSE
2003
IEEE-ACM
14 years 4 months ago
2003
IEEE-ACM
An information retrieval technique, latent semantic indexing, is used to automatically identify traceability links from system documentation to program source code. The results of...