Paper: A Lattice-based Framework for Joint Chinese Word Segmentation, POS Tagging and Parsing

ACL ID P13-2110
Title A Lattice-based Framework for Joint Chinese Word Segmentation, POS Tagging and Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

For the cascaded task of Chinese word seg- mentation, POS tagging and parsing, the pipe- line approach suffers from error propagation while the joint learning approach suffers from inefficient decoding due to the large combined search space. In this paper, we present a novel lattice-based framework in which a Chinese sentence is first segmented into a word lattice, and then a lattice-based POS tagger and a lat- tice-based parser are used to process the lattice from two different viewpoints: sequential POS tagging and hierarchical tree building. A strat- egy is designed to exploit the complementary strengths of the tagger and parser, and encour- age them to predict agreed structures. Experi- mental results on Chinese Treebank show that our lattice-based framework significantly im-...