Nonsymbolic Text Representation
arXiv:1610.00479
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 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.
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- Enriching Word Vectors with Subword Information
- Neural Machine Translation in Linear Time
- Character-Level Question Answering with Attention
- Gated Word-Character Recurrent Language Model
- Charagram: Embedding Words and Sentences via Character n-grams
- Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets
- Sharing Network Parameters for Crosslingual Named Entity Recognition