@inbook{2d0a13e7e5bb4a068bde81fe3adb3a54,
title = "A Universal Phrase Tagset for Multilingual Treebanks",
abstract = "Many syntactic treebanks and parser toolkits are developed in the past twenty years, including dependency structure parsers and phrase structure parsers. For the phrase structure parsers, they usually utilize different phrase tagsets for different languages, which results in an inconvenience when conducting the multilingual research. This paper designs a refined universal phrase tagset that contains 9 commonly used phrase categories. Furthermore, the mapping covers 25 constituent treebanks and 21 languages. The experiments show that the universal phrase tagset can generally reduce the costs in the parsing models and even improve the parsing accuracy.",
keywords = "Chinese word segmentation, information retrieval, machine translation, natural language understanding, text mining",
author = "Lifeng Han",
year = "2014",
month = sep,
day = "24",
doi = "10.1007/978-3-319-12277-9_22",
language = "English",
isbn = "9783319122762",
series = "Lecture Notes in Computer Science",
publisher = "Springer Cham",
pages = "247--258",
editor = "Sun, {Maosong } and Liu, {Yang } and Zhao, {Jun }",
booktitle = "Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data",
address = "Switzerland",
}