Distinguish Polarity in Bag-of-Words Visualization
Abstract
Neural network-based BOW models reveal that word-embedding vectors encode strong semantic regularities. However, such models are insensitive to word polarity. We show that, coupled with simple information such as word spellings, word-embedding vectors can preserve both semantic regularity and conceptual polarity without supervision. We then describe a nontrivial modification to the t-distributed stochastic neighbor embedding (t-SNE) algorithm that visualizes these semantic- and polarity-preserving vectors in reduced dimensions. On a real Facebook corpus, our experiments show significant improvement in t-SNE visualization as a result of the proposed modification.
Cite
Text
Xie et al. "Distinguish Polarity in Bag-of-Words Visualization." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.10963Markdown
[Xie et al. "Distinguish Polarity in Bag-of-Words Visualization." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/xie2017aaai-distinguish/) doi:10.1609/AAAI.V31I1.10963BibTeX
@inproceedings{xie2017aaai-distinguish,
title = {{Distinguish Polarity in Bag-of-Words Visualization}},
author = {Xie, Yusheng and Chen, Zhengzhang and Agrawal, Ankit and Choudhary, Alok N.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2017},
pages = {3344-3350},
doi = {10.1609/AAAI.V31I1.10963},
url = {https://mlanthology.org/aaai/2017/xie2017aaai-distinguish/}
}