论文信息 - An Application of the PDT-scheme to a Parallel Treebank

An Application of the PDT-scheme to a Parallel Treebank

Our paper comments on the divergences of the deep syntactic layers of Czech and English. We point out several phenomena potentially problematic for the syntactic alignment. We argue that at least some of the problems are caused by improper inferences from the deep syntactic layer of one language into the deep structures of the other one, and as such, they can be repaired on the theoretical level.

[1] Daniel Gildea,et al. The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[2] Alan Lee,et al. Proceedings of the 19th International Workshop on Treebanks and Linguistic Theories , 2006 .

[3] Bonnie J. Dorr,et al. Machine Translation Divergences: A Formal Description and Proposed Solution , 1994, CL.

[4] Ondrej Bojar,et al. Czech-English Word Alignment , 2006, LREC.

[5] Beatrice Santorini,et al. Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[6] Petr Sgall,et al. The Meaning Of The Sentence In Its Semantic And Pragmatic Aspects , 1986 .

[7] Andy Way,et al. Capturing translational divergences with a statistical tree-to-tree aligner , 2007 .

[8] W. J. Hutchins. Machine Translation: Past, Present, Future , 1986 .

[9] Silvie Cinková. From PropBank to EngValLex: Adapting the PropBank-Lexicon to the Valency Theory of the Functional Generative Description , 2006, LREC.