@InProceedings{kumar-bora:2018:W18-41,
  author    = {Kumar, Ritesh  and  Bora, Manas Jyoti},
  title     = {Part-of-Speech Annotation of English-Assamese code-mixed texts: Two Approaches},
  booktitle = {Proceedings of the First International Workshop on Language Cognition and Computational Models},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {94--103},
  abstract  = {In this paper, we discuss the development of a part-of-speech tagger for English-Assamese code-mixed texts. We provide a comparison of 2 approaches to annotating code-mixed data -- a) annotation of the texts from the two languages using monolingual resources from each language and b) annotation of the text through a different resource created specifically for code-mixed data. We present a comparative study of the efforts required in each approach and the final performance of the system. Based on this, we argue that it might be a better approach to develop new technologies using code-mixed data instead of monolingual, 'clean' data, especially for those languages where we do not have significant tools and technologies available till now.},
  url       = {http://www.aclweb.org/anthology/W18-4110}
}