Dear corpora users,<div>I'm doing a research on chunking of Slavic languages, including both chunking algorithms and the problem of chunk definitions for Slavic languages.</div><div><br></div><div>I'm aware of the following works:</div>
<div>• <b>Bulgarian</b>: P. Osenova's works on BaseNP chunking and transformation into HPSG (hand-written grammars)</div><div><meta http-equiv="content-type" content="text/html; charset=utf-8">• <b>Croatian</b>: works of K. Vučković (including her thesis), M. Tadić and Z. Dovedan (hand-written grammars, NooJ platform)</div>
<div>• <b>Polish</b>: works by A. Przepiórkowski (related to the Spejd formalism and the National Corpus of Polish) as well as those of me and M. Piasecki (a base NP chunker based on decision trees).</div><div>• <b>Serbo-Croatian</b>: works of G. Nenadić and D. Vitas (hand-writtern local grammars).</div>
<div><br></div><div><meta http-equiv="content-type" content="text/html; charset=utf-8">Probably the above list is incomplete, so I would be grateful if someone could point me to some more references. It is especially hard to find discussions on chunk definitions for Slavic languages.</div>
<div><br></div><div>Best,</div><div>Adam Radziszewski</div><div><br></div>