We report an empirical study on the role of syntactic features in building a semisupervised named entity (NE) tagger. Our study addresses two questions: What types of syntactic features are suitable for extracting potential NEs to train a classifier in a semi-supervised setting? How good is the resulting NE classifier on testing instances dissimilar from its training data? Our study shows that ...

Two annotations schemes for presenting the parsed structures are prevalent viz. the constituency structure and the dependency structure. While the constituency trees mark the relations due to positions, the dependency relations mark the semantic dependencies. Free word order languages like Sanskrit pose more problems for constituency parses since the elements within a phrase are dislocated. In ...

Constituency grammars originated with Leonard Bloomfield (1933) and were developed during the nineteen forties and nineteen fifties by a number of American structuralist linguists, including Harris (1946) and Wells (1947) — to mention just two. In the late nineteen fifties, Chomsky (1957) suggested that constituency grammars could be formalized as context free grammars. It is now clear that con...

In this study we show that constituency is of limited importance for a proper treatment of the interaction between the linear position of a wa-marked nominal in a Japanese sentence and possible domains of contrastive focus, and that constraints concerning contrastive focus should be represented in terms of linear order and not constituency. Linearisation HPSG, where linear order is independent ...

We present a statistical post-editing method for modifying the dependency labels in a dependency analysis. We test the method using two English datasets, three parsing systems and three labelled dependency schemes. We demonstrate how it can be used both to improve dependency label accuracy in parser output and highlight problems with and differences between constituency-to-dependency conversions.

We present a statistical post-editing method for modifying the dependency labels in a dependency analysis. We test the method using two English datasets, three parsing systems and three labelled dependency schemes. We demonstrate how it can be used both to improve label accuracy in parser output and highlight problems with and differences between constituency-to-dependency converters.

This research examines the factors that influence how members of the US House of Representatives vote. Party affiliation of the legislator and constituency interests will be the two main independent variables. The district's constituency characteristics are represented by constituency ideology ('96 Presidential vote for Clinton), percent non-white, region, and the median household education. Th...