Sequential Attention Module for Natural Language Processing (2109.03009v1)

Abstract: Recently, large pre-trained neural LLMs have attained remarkable performance on many downstream NLP applications via fine-tuning. In this paper, we target at how to further improve the token representations on the LLMs. We, therefore, propose a simple yet effective plug-and-play module, Sequential Attention Module (SAM), on the token embeddings learned from a pre-trained LLM. Our proposed SAM consists of two main attention modules deployed sequentially: Feature-wise Attention Module (FAM) and Token-wise Attention Module (TAM). More specifically, FAM can effectively identify the importance of features at each dimension and promote the effect via dot-product on the original token embeddings for downstream NLP applications. Meanwhile, TAM can further re-weight the features at the token-wise level. Moreover, we propose an adaptive filter on FAM to prevent noise impact and increase information absorption. Finally, we conduct extensive experiments to demonstrate the advantages and properties of our proposed SAM. We first show how SAM plays a primary role in the champion solution of two subtasks of SemEval'21 Task 7. After that, we apply SAM on sentiment analysis and three popular NLP tasks and demonstrate that SAM consistently outperforms the state-of-the-art baselines.