Polyseme-Aware Vector Representation for Text Classification

• Main Authors: Shun Guo, Nianmin Yao
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Polysemous words; context clustering algorithm; PAVRM-Context; PAVRM-Center
• Online Access: https://ieeexplore.ieee.org/document/9145584/

Representation models for text classification have recently shown impressive performance. However, these models neglect the importance of polysemous words in text. When polysemous words appear in a text, imprecise polysemous word embeddings will produce low-quality text representation that results in changing the original meaning of the text. To address this problem, in this paper, we present a more effective model architecture, the polyseme-aware vector representation model (PAVRM), to generate more precise vector representations for words and texts. The PAVRM can effectively identify polysemous words in a corpus with a context clustering algorithm. Additionally, we propose two methods to construct polysemous word representations, PAVRM-Context and PAVRM-Center. Experiments conducted on three standard text classification tasks and a custom text classification task demonstrate that the proposed PAVRM can be effectively introduced into existing models to generate higher-quality word and text representations to achieve better classification performance.