@InProceedings{stn-kurfal-can:2018:W18-30,
  author    = {Üstün, Ahmet  and  Kurfalı, Murathan  and  Can, Burcu},
  title     = {Characters or Morphemes: How to Represent Words?},
  booktitle = {Proceedings of The Third Workshop on Representation Learning for NLP},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {144--153},
  abstract  = {In this paper, we investigate the effects of using subword information in representa- tion learning. We argue that using syntactic subword units effects the quality of the word representations positively. We introduce a morpheme-based model and compare it against to word-based, character-based, and character n-gram level models. Our model takes a list of candidate segmentations of a word and learns the representation of the word based on different segmentations that are weighted by an attention mechanism. We performed experiments on Turkish as a morphologically rich language and English with a comparably poorer morphology. The results show that morpheme-based models are better at learning word representations of morphologically complex languages compared to character-based and character n-gram level models since the morphemes help to incorporate more syntactic knowledge in learning, that makes morpheme-based models better at syntactic tasks.},
  url       = {http://www.aclweb.org/anthology/W18-3019}
}