In this paper, we first analyze and classify the empty categories in a Hindi dependency treebank and then identify various discovery procedures to automatically detect the existe...
Chaitanya G. S. K., Samar Husain, Prashanth Mannem
We are in the process of creating a multi-representational and multi-layered treebank for Hindi/Urdu (Palmer et al., 2009), which has three main layers: dependency structure, pred...
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...
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...
This paper describes a parser which generates parse trees with empty elements in which traces and fillers are co-indexed. The parser is an unlexicalized PCFG parser which is guara...