@InProceedings{hu-dakota-kubler:2017:RANLP,
  author    = {Hu, Hai  and  Dakota, Daniel  and  K\"{u}bler, Sandra},
  title     = {Non-Deterministic Segmentation for Chinese Lattice Parsing},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {316--324},
  abstract  = {Parsing Chinese critically depends on correct word segmentation for the parser
	since incorrect segmentation inevitably causes              incorrect parses. We
	investigate a pipeline approach to segmentation and parsing using word lattices
	as parser input. We compare CRF-based and  lexicon-based approaches to word
	segmentation. Our results show that the lattice parser is capable of selecting
	the correction segmentation from thousands of options, thus drastically
	reducing the number of unparsed sentence. Lexicon-based parsing models have a
	better coverage than the CRF-based approach, but the many options are more
	difficult to handle. We reach our best result by using a lexicon from the
	n-best CRF analyses,  combined with highly probable words.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_043}
}

