@InProceedings{ni-dinu-florian:2017:Long,
  author    = {Ni, Jian  and  Dinu, Georgiana  and  Florian, Radu},
  title     = {Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {1470--1480},
  abstract  = {The state-of-the-art named entity recognition (NER) systems are supervised
	machine learning models that require large amounts of manually annotated data
	to achieve high accuracy. However, annotating NER data by human is expensive
	and time-consuming, and can be quite difficult for a new language. In this
	paper, we present two weakly supervised approaches for cross-lingual NER with
	no human annotation in a target language. The first approach is to create
	automatically labeled NER data for a target language via annotation projection
	on comparable corpora, where we develop a heuristic scheme that effectively
	selects good-quality projection-labeled data from noisy data. The second
	approach is to project distributed representations of words (word embeddings)
	from a target language to a source language, so that the source-language NER
	system can be applied to the target language without re-training. We also
	design two co-decoding schemes that effectively combine the outputs of the two
	projection-based approaches. We evaluate the performance of the proposed
	approaches on both in-house and open NER data for several target languages. The
	results show that the combined systems outperform three other weakly supervised
	approaches on the CoNLL data.},
  url       = {http://aclweb.org/anthology/P17-1135}
}