Enhanced UrduAspectNet: Leveraging Biaffine Attention for superior Aspect-Based Sentiment Analysis

Kamran Aziz, Naveed Ahmed, Hassan Jalil Hadi, Aizihaierjiang Yusufu, Mohammed Ali Alshara, Yasir Javed, Donghong JiJ. King Saud Univ. Comput. Inf. Sci 2024 · OpenReview

Abstract

Urdu, with its rich linguistic complexity, poses significant challenges for computational sentiment analysis. This study presents an enhanced version of UrduAspectNet, specifically designed for Aspect-Based Sentiment Analysis (ABSA) in Urdu. We introduce key innovations including the incorporation of Biaffine Attention into the model architecture, which synergizes XLM-R embeddings, a bidirectional LSTM (BiLSTM), and dual Graph Convolutional Networks (GCNs). Additionally, we utilize dependency parsing to create the adjacency matrix for the GCNs, capturing syntactic dependencies to enhance relational representation. The improved model, termed Enhanced UrduAspectNet, integrates POS and lemma embeddings, processed through BiLSTM and GCN layers, with Biaffine Attention enhancing the extraction of intricate aspect and sentiment relationships. We also introduce the use of BIO tags for aspect term identification, improving the granularity of aspect extraction. Experimental results demonstrate significant improvements in both aspect extraction and sentiment classification accuracy. This research advances Urdu sentiment analysis and sets a precedent for leveraging sophisticated NLP techniques in underrepresented languages.
BibTeX
@article{aziz2024enhanced,
  author = {Kamran Aziz and Naveed Ahmed and Hassan Jalil Hadi and Aizihaierjiang Yusufu and Mohammed Ali Alshara and Yasir Javed and Donghong Ji},
  title = {{Enhanced UrduAspectNet: Leveraging Biaffine Attention for superior Aspect-Based Sentiment Analysis}},
  journal = {J. King Saud Univ. Comput. Inf. Sci.},
  year = {2024},
  url = {https://openreview.net/forum?id=6g2yUL5qwM},
}

Loading related content...

Figure