@InProceedings{zhang-EtAl:2016:COLING1,
  author    = {Zhang, Dongxu  and  Zhang, Boliang  and  Pan, Xiaoman  and  Feng, Xiaocheng  and  Ji, Heng  and  XU, Weiran},
  title     = {Bitext Name Tagging for Cross-lingual Entity Annotation Projection},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {461--470},
  abstract  = {Annotation projection is a practical method to deal with the low resource
	problem in incident languages (IL) processing. Previous methods on annotation
	projection mainly relied on word alignment results without any training
	process, which led to noise propagation caused by word alignment errors. In
	this paper, we focus on the named entity recognition (NER) task and propose a
	weakly-supervised framework to project entity annotations from English to IL
	through bitexts. Instead of directly relying on word alignment results, this
	framework combines advantages of rule-based methods and deep learning methods
	by implementing two steps: First, generates a high-confidence entity annotation
	set on IL side with strict searching methods; Second, uses this high-confidence
	set to weakly supervise the model training. The model is finally used to
	accomplish the projecting process. Experimental results on two low-resource ILs
	show that the proposed method can generate better annotations projected from
	English-IL parallel corpora. The performance of IL name tagger can also be
	improved significantly by training on the newly projected IL annotation set.},
  url       = {http://aclweb.org/anthology/C16-1045}
}

