A Quantum-Inspired Complex-Valued Representation for Encoding Sentiment Information (Student Abstract)

Guangcheng Liu, Yuexian Hou, Shikai Song

AAAI 2021 pp. 15831-15832

doi:10.1609/AAAI.V35I18.17912 /aaai/2021/liu2021aaai-quantum/

Abstract

Recently, a Quantum Probability Drive Network (QPDN) is proposed to model different levels of semantic units by extending word embedding to complex-valued representation (CR). The extended complex-valued embeddings are still insensitive to polarity causing that they generalize badly in sentiment analysis (SA). To solve it, we propose a method of encoding sentiment information into sentiment words for SA. Attention mechanism and an auxiliary task are introduced to help learn the CR of sentiment words with the help of the sentiment lexicon. We use the amplitude part to represent the distributional information and the phase part to represent the sentiment information of the language. Experiments on three popular SA datasets show that our method is effective.

PDF AAAI Semantic Scholar

Cite

Text

Liu et al. "A Quantum-Inspired Complex-Valued Representation for Encoding Sentiment Information (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17912

Markdown

[Liu et al. "A Quantum-Inspired Complex-Valued Representation for Encoding Sentiment Information (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/liu2021aaai-quantum/) doi:10.1609/AAAI.V35I18.17912

BibTeX

@inproceedings{liu2021aaai-quantum,
  title     = {{A Quantum-Inspired Complex-Valued Representation for Encoding Sentiment Information (Student Abstract)}},
  author    = {Liu, Guangcheng and Hou, Yuexian and Song, Shikai},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15831-15832},
  doi       = {10.1609/AAAI.V35I18.17912},
  url       = {https://mlanthology.org/aaai/2021/liu2021aaai-quantum/}
}