A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification


  • Zeyang Lei Tsinghua University
  • Yujiu Yang Tsinghua University
  • Min Yang The University of Hong Kong
  • Wei Zhao Tecent
  • Jun Guo Tsinghua University
  • Yi Liu Peking University Shenzhen Institute




In this paper, we propose a novel Human-like Semantic Cognition Network (HSCN) for aspect-level sentiment classification, motivated by the principles of human beings’ reading cognitive process (pre-reading, active reading, post-reading). We first design a word-level interactive perception module to capture the correlation between context words and the given target words, which can be regarded as pre-reading. Second, to mimic the process of active reading, we propose a targetaware semantic distillation module to produce the targetspecific context representation for aspect-level sentiment prediction. Third, we further devise a semantic deviation metric module to measure the semantic deviation between the targetspecific context representation and the given target, which evaluates the degree we understand the target-specific context semantics. The measured semantic deviation is then used to fine-tune the above active reading process in a feedback regulation way. To verify the effectiveness of our approach, we conduct extensive experiments on three widely used datasets. The experiments demonstrate that HSCN achieves impressive results compared to other strong competitors.




How to Cite

Lei, Z., Yang, Y., Yang, M., Zhao, W., Guo, J., & Liu, Y. (2019). A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6650-6657. https://doi.org/10.1609/aaai.v33i01.33016650



AAAI Technical Track: Natural Language Processing