@InProceedings{silfverberg-hulden:2017:SCLeM,
  author    = {Silfverberg, Miikka  and  Hulden, Mans},
  title     = {Weakly supervised learning of allomorphy},
  booktitle = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {46--56},
  abstract  = {Most NLP resources that offer annotations at the word segment level provide
	morphological annotation that includes features indicating tense, aspect,
	modality, gender, case, and other inflectional information.  Such information
	is rarely aligned to the relevant parts of the words---i.e. the allomorphs, as
	such annotation would be very costly.  These unaligned weak labelings are
	commonly provided by annotated NLP corpora such as treebanks in various
	languages.  Although they lack alignment information, the presence/absence of
	labels at the word level is also consistent with the amount of supervision
	assumed to be provided to L1 and L2 learners. In this paper, we explore several
	methods to learn this latent alignment between parts of word forms and the
	grammatical information provided.  All the methods under investigation favor
	hypotheses regarding allomorphs of morphemes that re-use a small inventory,
	i.e. implicitly minimize the number of allomorphs that a morpheme can be
	realized as.  We show that the provided information offers a significant
	advantage for both word segmentation and the learning of allomorphy.},
  url       = {http://www.aclweb.org/anthology/W17-4107}
}