Automatic Transformation of the Thai Categorial Grammar Treebank to Dependency Trees

TY - GEN

T1 - Automatic Transformation of the Thai Categorial Grammar Treebank to Dependency Trees

AU - Rishøj, Christian

AU - Ruangrajitpakorn, Taneth

AU - Boonkwan, Prachya

AU - Supnithi, Thepchai

PY - 2011/11

Y1 - 2011/11

N2 - A method for deriving an approximately labeled dependency treebank from the Thai Categorial Grammar Treebank has been implemented. The method involves a lexical dictionary for assigning dependency directions to the CG types associated with the grammatical entities in the CG bank, falling back on a generic mapping of CG types in case of unknown words. Currently, all but a handful of the trees in the Thai CG bank can unambiguously be transformed into directed dependency trees. Dependency labels can optionally be assigned with a learned classifier, which in a preliminary evaluation with a very small training set achieves 76.5% label accuracy. In the process, a number of annotation errors in the CG bank were identified and corrected. Although rather limited in its coverage, excluding e.g. long-distance dependencies, topicalisations and longer sentences, the resulting treebank is believed to be sound in terms of structural annotational consistency and a valuable complement to the scarce Thai language resources in existence.

AB - A method for deriving an approximately labeled dependency treebank from the Thai Categorial Grammar Treebank has been implemented. The method involves a lexical dictionary for assigning dependency directions to the CG types associated with the grammatical entities in the CG bank, falling back on a generic mapping of CG types in case of unknown words. Currently, all but a handful of the trees in the Thai CG bank can unambiguously be transformed into directed dependency trees. Dependency labels can optionally be assigned with a learned classifier, which in a preliminary evaluation with a very small training set achieves 76.5% label accuracy. In the process, a number of annotation errors in the CG bank were identified and corrected. Although rather limited in its coverage, excluding e.g. long-distance dependencies, topicalisations and longer sentences, the resulting treebank is believed to be sound in terms of structural annotational consistency and a valuable complement to the scarce Thai language resources in existence.

M3 - Article in proceedings

BT - Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP)

PB - Association for Computational Linguistics

ER -