Current advances in shallow parsing and machine learning allow us to use results from these fields in a methodology for Authorship Attribution. We report on experiments with a corpus that consists of newspaper articles about national current affairs by different journalists from the Belgian newspaper De Standaard. Because the documents are in a similar genre, register, and range of topics, toke...

Current advances in shallow parsing and machine learning allow us to use results from these fields in a methodology for Authorship Attribution. We report on experiments with a corpus that consists of newspaper articles about national current affairs by different journalists from the Belgian newspaper De Standaard. Because the documents are in a similar genre, register, and range of topics, toke...

This paper presents a multi-dialect, multi-genre, human annotated corpus of dialectal Arabic with data obtained from both online newspaper commentary and Twitter. Most Arabic corpora are small and focus on Modern Standard Arabic (MSA). There has been recent interest, however, in the construction of dialectal Arabic corpora (Zaidan and Callison-Burch, 2011a; Al-Sabbagh and Girju, 2012). This wor...

Ever since the formulation of Rhetorical Structure Theory (RST) by Mann and Thompson, researchers have debated about what is the ‘right’ number of relations. One proposal is based on the discourse markers (connectives) signalling the presence of a particular relationship. In this paper, I discuss the adequacy of such a proposal, in the light of two different corpus studies: a study of conversat...

The current study focuses on the similarities and differences of conceptual metaphor and metonymy between each genre in newspaper headlines. Headlines in news articles in Apple Daily from May 21 to May 27 were collected and analyzed. There are three basic findings. First, blocks for entertainment and sports used, in proportion, more metaphors and metonymies than any other blocks. Second, the id...

Popularly considered a great equalizer, death and the rituals around it nevertheless accentuate social distinctions. The present study focuses on a sample (N = 2554) of death announcements in a major Turkish daily newspaper (Hürriyet) from 1970 to 2006. Out of the liminal position of Turkish death announcements between obituaries and death notices emerges a large decentralized collection of pri...

In this paper, we discuss tree kernels that can be applied for the classification of XML documents based on their DOM trees. DOM trees are ordered trees, in which every node might be labeled by a vector of attributes including its XML tag and the textual content. We describe four new kernels suitable for this kind of trees: a tree kernel derived from the well-known parse tree kernel, the set tr...

Mode and genre transformations are main issues in the digital era, especially apparent when news interviews are adapted into written news reports. This paper investigates how interactions in a television news interview are excerpted and adapted into a written news text in newspapers. Through a text analysis of two political interviews in Taiwan on television, and five newspaper reports based on...

This paper describes the La Repubblica corpus, currently being developed at the SSLMIT of the University of Bologna. The corpus is a very large collection of newspaper text, currently amounting to 175 million words, but expected to grow to 400 million before the end of 2004. When completed, it will contain all the articles published between 1985 and 2000 by the national daily La Repubblica. The...