🤖 AI Summary
This work addresses the limitation of traditional HAL models in text classification, where mean pooling treats all tokens uniformly and consequently dilutes critical semantic information. To overcome this, we propose a novel approach that integrates a learnable temperature-scaled additive attention mechanism into the pooling stage of HAL, coupled with truncated singular value decomposition (SVD) for dimensionality reduction. This design enables the model to adaptively emphasize sentiment-relevant keywords while suppressing stop words, yielding more discriminative sentence-level representations. Evaluated on the IMDB dataset, our method achieves a test accuracy of 82.38%, representing a 6.74 percentage point improvement over the mean-pooling baseline. Attention visualization further confirms the model’s capacity to effectively attend to salient sentiment-bearing words, enhancing both performance and interpretability.
📝 Abstract
The Hyperspace Analogue to Language (HAL) model relies on global word co-occurrence matrices to construct distributional semantic representations. While these representations capture lexical relationships effectively, aggregating them into sentence-level embeddings via standard mean pooling often results in information loss. Mean pooling assigns equal weight to all tokens, thereby diluting the impact of contextually salient words with uninformative structural tokens. In this paper, we address this limitation by integrating a learnable, temperature-scaled additive attention mechanism into the HAL representation pipeline. To mitigate the sparsity and high dimensionality of the raw co-occurrence matrices, we apply Truncated Singular Value Decomposition (SVD) to project the vectors into a dense latent space prior to the attention layer. We evaluate the proposed architecture on the IMDB sentiment analysis dataset. Empirical results demonstrate that the attention-based pooling approach achieves a test accuracy of 82.38%, yielding an absolute improvement of 6.74 percentage points over the traditional mean pooling baseline (75.64%). Furthermore, qualitative analysis of the attention weights indicates that the mechanism successfully suppresses stop-words and selectively attends to sentiment-bearing tokens, improving both classification performance and model interpretability.