«Traditionally, unification grammars are hand-coded. This is extremely time consuming, expensive and very difficult to scale. [...] we have developed a new method for automatically extracting wide-coverage probabilistic unification (LFG) grammars from treebank resources. To achieve this, we first automatically annotate the treebank (such as Penn-II) with feature-structure information (LFG f-structures, approximating to basic predicate-argument structure). From the f-structure annotated treebank, we then automatically extract wide-coverage, probabilistic LFG approximations to parse new text»
«takes as input a sequence of phrase-structure trees and modifies their labels according to a set of rules. ... Its rule notation is flexible enough to emulate head/argument-finding rules»
J. DeNero, und D. Klein. Proceedings of ACL-08: HLT, Short Papers, Seite 25--28. Columbus, Ohio, Association for Computational Linguistics, (Juni 2008)
T. Lech, und K. Smedt. Proceedings from the first Bergen Workshop on Anaphora Resolution (WAR I), Seite 26--38. Newcastle upon Tyne, Cambridge Scholars Publishing, (2007)
P. Fung, Z. Wu, Y. Yang, und D. Wu. TMI-2007: Proceedings of the 11 th International Conference on Theoretical and Methodological Issues in Machine Translation, Seite 75--84. Skövde, Sweden, (2007)
C. Callison-Burch, M. Osborne, und P. Koehn. Proceedings the Eleventh Conference of the European Chapter of the Association for Computational Linguistics, Seite 249--256. Trento, Italia, (2006)
Y. Samuelsson, und M. Volk. Treebanking for Discourse and Speech. Proceedings of the NODALIDA 2005 Special Session on Treebanks for Spoken Language and Discourse, Volume 32 von Copenhagen Studies in Language, Seite 147. Forlaget Samfundslitteratur, København, (2005)