Abstract
We introduce the first generic text representation model that is completely nonsymbolic, i.e., it does not require the availability of a segmentation or tokenization method that attempts to identify words or other symbolic units in text. This applies to training the representations as well as to using them in an application. We demonstrate better performance than prior work on entity typing and text denoising.
Cite
CITATION STYLE
Schütze, H. (2017). Nonsymbolic text representation. In 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference (Vol. 2, pp. 785–796). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/e17-1074
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
