@InProceedings{liu-nouvel:2017:I17-1,
  author    = {Liu, Luigi (Yu-Cheng)  and  Nouvel, Damien},
  title     = {A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {694--703},
  abstract  = {In many languages such as Bambara or Arabic, tone markers (diacritics) may be
	written but are actually often omitted. NLP applications are confronted to
	ambiguities and subsequent difficulties when processing texts. To circumvent
	this problem, tonalization may be used, as a word sense disambiguation task,
	relying on context to add diacritics that partially disambiguate words as well
	as senses. In this paper, we describe our implementation of a Bambara tonalizer
	that adds tone markers using machine learning (CRFs). To make our tool
	efficient, we used differential coding, word segmentation and edit operation
	filtering. We describe our approach that allows tractable machine learning and
	improves accuracy: our model may be learned within minutes on a 358K-word
	corpus and reaches 92.3% accuracy.},
  url       = {http://www.aclweb.org/anthology/I17-1070}
}