A Quantum-inspired Complex-valued Representation for Encoding Sentiment Information (Student Abstract)

Authors

  • Guangcheng Liu College of Computer Science and Technology, Tianjin University, Tianjin, China
  • Yuexian Hou College of Computer Science and Technology, Tianjin University, Tianjin, China
  • Shikai Song College of Computer Science and Technology, Tianjin University, Tianjin, China

Keywords:

Word Embedding, Sentiment Analysis, Quantum Theory

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.

Downloads

Published

2021-05-18

How to Cite

Liu, G., Hou, Y., & Song, S. (2021). A Quantum-inspired Complex-valued Representation for Encoding Sentiment Information (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15831-15832. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17912

Issue

Section

AAAI Student Abstract and Poster Program