English

Multi-modal Sentiment Analysis using Super Characters Method on Low-power CNN Accelerator Device

Computation and Language 2020-01-29 v1

Abstract

Recent years NLP research has witnessed the record-breaking accuracy improvement by DNN models. However, power consumption is one of the practical concerns for deploying NLP systems. Most of the current state-of-the-art algorithms are implemented on GPUs, which is not power-efficient and the deployment cost is also very high. On the other hand, CNN Domain Specific Accelerator (CNN-DSA) has been in mass production providing low-power and low cost computation power. In this paper, we will implement the Super Characters method on the CNN-DSA. In addition, we modify the Super Characters method to utilize the multi-modal data, i.e. text plus tabular data in the CL-Aff sharedtask.

Keywords

Cite

@article{arxiv.2001.10179,
  title  = {Multi-modal Sentiment Analysis using Super Characters Method on Low-power CNN Accelerator Device},
  author = {Baohua Sun and Lin Yang and Hao Sha and Michael Lin},
  journal= {arXiv preprint arXiv:2001.10179},
  year   = {2020}
}

Comments

9 pages, 2 figures, 6 tables. Accepted by AAAI 2020 Affective Content Analysis Workshop

R2 v1 2026-06-23T13:22:33.804Z