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 parameters of the model on a training corpus as well as to applying it when computing the representation of a new text. We show that our model performs better than prior work on an information extraction and a text denoising task.
Cite
@article{arxiv.1610.00479,
title = {Nonsymbolic Text Representation},
author = {Hinrich Schuetze and Heike Adel and Ehsaneddin Asgari},
journal= {arXiv preprint arXiv:1610.00479},
year = {2017}
}